ChatPPG.
Join free
Dataset

Emognition

wearable emotion film-clip dataset (E4 + Galaxy Watch + Muse 2)

PPGIMUEDATempEEGHarvard dataverseRaw waveforms
Get data DOI Cite

Saganowski et al., Scientific Data 2022 (10.1038/s41597-022-01262-0). Participants watched short film clips eliciting amusement, awe, enthusiasm, liking, surprise, anger, disgust, fear, sadness. Upper-body video + wearables.

At a glance
Type
Dataset
Host
Harvard dataverse (opens in a new tab)
DOI
10.7910/DVN/R9WAF4 (opens in a new tab)
Licence
Not reported
Access
Not reported
Subjects
43
Signals
PPGIMUEDATempEEG
Devices
PPG sites
Wrist
Setting
Lab
Wrist
Yes
Raw waveforms
Yes
Tasks
Emotion
Updated
Oct 27, 2026

Original description

The Emognition dataset is dedicated to testing methods for emotion recognition (ER) from physiological responses and facial expressions. We collected data from 43 participants who watched short film clips eliciting nine discrete emotions: amusement, awe, enthusiasm, liking, surprise, anger, disgust, fear, and sadness. Three wearables were utilized to record physiological data: EEG, BVP (2x), HR, EDA, SKT, ACC (3x), and GYRO (2x), alongside the upper-body video recordings. After each film clip, participants completed two types of self-reports, i.e., related to nine discrete emotions and three dimensional ones: valence, arousal, motivation. The obtained data facilitates various ER approaches, e.g.,multimodal ER, EEG- vs. cardiovascular-based ER, discrete to dimensional representation transitions. The technical validation supported that watching film clips elicited the targeted emotions.

Verbatim fromDataCite· Licence: info:eu-repo/semantics/closedAccess

Emognition: ChatPPG research summary card

Key numbers

43
Subjects
1
Reference labels
EMOTION
32Hz
Released sampling rate
E4: BVP 64Hz, EDA/TEMP 4Hz, ACC 32Hz; Galaxy Watch BVP + ACC/GYRO; Muse 2 EEG

How it works

How Emognition works: Devices & body sites → Signals recorded → TasksDevices & body sites: Empatica E4 (Empatica · Wrist). PPG sites: Wrist. Signals recorded: Emognition, 43 subjects · 32Hz, signals PPG, IMU, EDA, Temperature, EEG. Tasks: Stress.Devices & body sitesEmpatica E4: Empatica · WristEmpatica E4Empatica · WristPPG sites: WristPPG sitesWristSignals recordedEmognition43 subjects · 32HzPPGxyzIMUEDATemperatureEEGTasksStressStress

No model in the hub reports results on this dataset yet.

Sampling
E4: BVP 64Hz, EDA/TEMP 4Hz, ACC 32Hz; Galaxy Watch BVP + ACC/GYRO; Muse 2 EEG
Reference labels
emotion
Device roles
Study wearable (IMU)

Devices· 1

Product photograph of a black Empatica E4 wristband, seen from above
Empatica E4
Empatica · Wrist
PPGIMUEDATemp
Product image: Empatica

Full photo credits, sources and licences are on each device page.

Models trained or evaluated on it

No model in the hub reports results on Emognition yet. Be the first: results submitted with a paper are added here.

Papers using it· 1

FAQ

How many subjects are in Emognition?

Emognition has data from 43 subjects, as listed in its research record.

What signals does Emognition include?

Emognition includes PPG, EDA, accelerometer, skin temperature, EEG and gyroscope data. Sampling rate as recorded: E4: BVP 64Hz, EDA/TEMP 4Hz, ACC 32Hz; Galaxy Watch BVP + ACC/GYRO; Muse 2 EEG. Raw waveforms are included.

What can Emognition be used for?

Research tasks it supports: emotion recognition. Reference labels: emotion.

How do I get Emognition, and what is its licence?

It is available from https://doi.org/10.7910/DVN/R9WAF4. No licence is recorded for it here, so check the terms on the source page before you use it.

Was Emognition recorded with a wrist-worn device?

Yes. Its record lists wrist-worn recording.

Cite

APA

Emognition [Data set]. (n.d.). harvard-dataverse. https://doi.org/10.7910/DVN/R9WAF4

BibTeX

@misc{emognitionemognition,
  title         = {{Emognition}},
  howpublished  = {harvard-dataverse},
  doi           = {10.7910/DVN/R9WAF4}
}

Built from the hub record. Check it against the publisher before submitting.

Cite the ChatPPG record

Cite the dated snapshot 2026-10 for a fixed, reproducible version. Please also cite the original publications listed above.

APA

ChatPPG. (2026). Emognition: dataset record (Version 2026-10) [Data set]. ChatPPG Research Hub. https://chatppg.com/research/datasets/emognition

BibTeX
@misc{chatppg_dataset_emognition,
  author       = {{ChatPPG}},
  title        = {{Emognition: dataset record}},
  year         = {2026},
  month        = oct,
  version      = {2026-10},
  howpublished = {\url{https://chatppg.com/research/datasets/emognition}},
  note         = {ChatPPG Research Hub, Snapshot 2026-10, https://chatppg.com/research/snapshots/2026-10}
}
CITATION.cff
cff-version: 1.2.0
message: "If you use this resource, please cite it as below."
type: dataset
title: "Emognition: dataset record"
authors:
  - name: "ChatPPG"
url: "https://chatppg.com/research/datasets/emognition"
repository-artifact: "https://chatppg.com/research/snapshots/2026-10"
version: "2026-10"
date-released: "2026-10-27"

History

  1. Record updated

Articles and algorithm explainers

Same tasks, signals and research

Papers

Datasets