concept
active
concept:functional-emotions

Functional Emotions

Sofroniew et al.'s causally functional emotion-concept representations discovered in Claude Sonnet 4.5.

Neighborhood — ranked by edge-count

Frameworks (2)

framework
  • Theory of consciousness where metacognitive representations are necessary for conscious experience.
  • Seth's predictive-processing account grounding consciousness in interoceptive inference and organismic regulation.

Methods (1)

method
  • Persona Vectors
    associated_with
    Directions in activation space encoding a model's dispositional self-presentation, used as evidence for self-modelling.

Findings (1)

finding

Related by similarity (8)

cosine ≥ 0.65 · no typed edge

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

  • Functionalismframework0.777
    Epistemological position that what any phenomenon is is its causal/operational role; rejects hidden essence; foundational to CIMC's stance
  • functional valenceconcept0.773
    Valence as a functional property, proposed to act as dimensionality reduction when parallel processing paths interfere.
  • Feelingsconcept0.770
    Salient vectors in the space of emotions and intuitions; percepts of emotion, physiological valence, and extra-intellectual evaluation of reality
  • Empirical effect where intervening on one feature induces coherent shifts across multiple linguistic dimensions aligned with the target attribute.
  • Alexander distinguishes 'feeling' — the sense of being part of the ocean, sky, world — from emotions like happiness, sadness, or anger
  • One of the three major competing approaches to parallel programming mentioned in the paper; used for comparison with Linda.
  • The deep fit between a building's form and its functional requirements, achieved only through differentiation.
  • Functional Tokenconcept0.750
    A discrete token in the vocabulary that represents a visual operation (e.g., <|Line|>, <|Shape|>, <|Text|>), generated via next-token prediction within autoregressive sequences.