We map the full spectrum of emotion with AI

Our research aligns foundation models with human well-being





1 million+


AI models of emotional expression

Traditional theories posited six discrete emotions, but we’ve discovered that emotional behavior is better explained by a high-dimensional, continuous space

Speech Prosody

Discover over 25 patterns of tune, rhythm, and timbre




Amusement, Anger, Awkwardness, Boredom, Calmness, Confusion, Contempt, Desire, Determination, Distress, Fear, Guilt, Horror, Pain, Pride, Sadness, Surprise, and Tiredness


Speech Prosody


Research highlights

A high-dimension map of expressive behavior

Semantic space theory

We’ve introduced datasets and machine learning methods to explore the dimensions of meaning underlying the feelings we report. We find nuanced patterns of expression in the face, voice, and beyond, replacing low-dimensional theories with a high-dimensional, data-driven understanding of human emotional expression. These discoveries provide a new foundation for emotion science and empathic AI.

Explore findings
smiling boy

28 nuanced facial expressions

The face

We’ve collected millions of natural facial expressions worldwide. Our findings reveal that facial expressions are more complex and nuanced than previously assumed. Our facial expression models replace time-consuming approaches to behavioral measurement with automated analysis.

Explore findings
smiling girl

Interpreting the value of laughs, cries, and sighs

The voice

The voice is even richer with nonverbal cues than facial expressions. We pioneered decoding subtle qualities in speech prosody: intonation, timbre, and rhythm. We go beyond language by understanding how something is said, not just what is said. We also study “vocal bursts” including sighs, gasps, grunts, laughs, shrieks, oohs, and ahhs. This work unlocks a parallel channel of information in the voice that was previously overlooked by AI.

Explore findings
guy in yellow t-shirt, blurred emotions


Discover the research foundational to our products

  • Sixteen facial expressions occur in similar contexts worldwide

  • What music makes us feel: At least 13 dimensions organize subjective experiences associated with music across different cultures

    PNAs logo
  • Self-report captures 27 distinct categories of emotion bridged by continuous gradients

    Pnas logo
  • Universal facial expressions uncovered in art of the ancient Americas: A computational approach

    Science Advances logo
  • Mapping the passions: Toward a high-dimensional taxonomy of emotional experience and expression

    Trends in Cognitive Sciences logo
  • The neural representation of visually evoked emotion Is high-dimensional, categorical, and distributed across transmodal brain regions

    iScience logo
  • GoEmotions: A dataset of fine-grained emotions

    ACL logo
  • Facial movements have over twenty dimensions of perceived meaning that are only partially captured with traditional methods

    PsyArxiv logo
  • The primacy of categories in the recognition of 12 emotions in speech prosody across two cultures

    Nature human behaviour logo
  • How emotion is experienced and expressed in multiple cultures: a large-scale experiment

    PsyArxiv logo
  • Semantic Space Theory: Data-driven insights into basic emotions

    CDPS logo
  • Deep learning reveals what vocal bursts express in different cultures

    Nature human behaviour logo
  • The MuSe 2022 Multimodal Sentiment Analysis Challenge: Humor, Emotional Reactions, and Stress

  • How emotions, relationships, and culture constitute each other: Advances in social functionalist theory

    Cognition and Emotion logo
  • Intersectionality in emotion signaling and recognition: The influence of gender, ethnicity, and social class

    Emotion journal logo
  • Mapping 24 emotions conveyed by brief human vocalization

    American Psychologist
  • What the face displays: Mapping 28 emotions conveyed by naturalistic expression

    American Psychologist
  • The ICML 2022 Expressive Vocalizations Workshop and Competition: Recognizing, generating, and personalizing vocal bursts

    ICML2022 logo
  • The ACII 2022 Affective Vocal Bursts Workshop & Competition: Understanding a critically understudied modality of emotional expression

  • Emotional expression: Advances in basic emotion theory

    Jnb 01.png

Join us in building the future of empathic technology

Careers at hume