He found himself avoiding eye contact with Mr. Henderson, the resident from 3B who always seemed to be impeccably dressed. David had bumped into him in the lobby, and the man had been going on about 'investment potential' in hushed tones. David’s usual easygoing smile had vanished, replaced by a tight-lipped grimace. His shoulders tensed.

He spent the evening rearranging his meager possessions. His collection of comic books, stacked haphazardly on a shelf, seemed embarrassingly childish. His old, threadbare couch now felt like a glaring symbol of his limited means.

He caught his reflection in the window, seeing a rumpled man with messy hair. He ran a hand through it, wishing he could somehow disappear into the shadows. The thought of potential buyers touring his place filled him with an unexpected dread.

Emotion: self-conscious

Cluster: Embarrassment
PC1 (Valence): -1.03 Negative
PC2 (Disposition): 0.52

Role in Research

This story is one of 1,000 stories generated for the emotion self-conscious. During extraction, it was fed through Gemma4-31B and its hidden state activations were captured at 11 layers.

The mean activation across all 1,000 self-conscious stories, after denoising with neutral dialogue baselines, produces the self-conscious emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the self-conscious vector is projected through the unembedding matrix.

Promoted:
S0.307
C0.298
ness0.273
尴尬0.263
😶0.242
Suppressed:
que-0.399
de-0.266
triumphant-0.266
আনন্দের-0.247
ايا-0.238