The cafeteria was a cacophony of hushed conversations and clattering trays. Liam, standing in the line, found himself compulsively straightening his already-perfectly-aligned backpack straps. Each chew of his classmates, each rustle of a napkin, felt pointed.

He felt the prickle of sweat on his forehead. The aroma of pizza and coffee, usually comforting, now nauseated him. The food smelled of failure, of an uncertain future. He just wanted to leave and be alone.

He quickly scanned the room, desperately seeking an empty table, a refuge from the penetrating gazes. His reflection in the window seemed to be a perfect stranger.

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