We hypothesize that persistently active emotional state representations exist in LLMs but may be missed by standard probing methods.

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

• To what extent is there persistence of emotional state beyond what is expected merely from the autoregressive nature of LLMs?question0.861
  The central research question motivating the paper
• Emotion features in LLMs are genuinely more persistent than variance-matched random features, indicating stateful emotional encoding beyond autoregressive dynamicsclaim0.854
  Central interpretive claim of the paper supported by multiple convergent analyses
• Are LLM emotion states encoded only selectively in token positions where they are operative, or in a more complex non-linear manner?question0.839
  Question raised by Anthropic and partially addressed by this paper's persistence evidence
• We hypothesize that emotion states are more persistent because they correspond to genuinely stateful internal representations, not merely local surface contenthypothesis0.827
  Proposed explanation for why emotion probes are more persistent than variance-matched random probes
• LLM representations exhibit intriguing patterns under spatio-permutational analyses, suggesting a potentially profound yet tentative indication of consciousness.claim0.818
  Qualified positive claim from spatio permutation analysis where two cases satisfy all three criteria.
• "Our findings demonstrate that LLMs can compute meaningful functions over perturbations to their internal states, establishing introspection as a real but layer-dependent phenomenon that merits further investigation."quote0.804
  Central thesis statement of the paper
• Emotion refers to a state concept, so stateful representations in general may be more persistent across tokens.claim0.800
  Interpretive hypothesis offered to explain why emotion features are more persistent
• We hypothesize that 'consciousness' phenomena can be observed in the internal states of an LLM, specifically in its learned representations when analyzed as a sequence.hypothesis0.795
  Primary research hypothesis driving the entire study; operationalized via three criteria.