The bookstore was crammed, a haven for quiet reflection that felt, at the moment, like a crowded fishbowl. Leo’s cheeks burned as he browsed the used paperback section. He imagined every shopper scrutinizing his choice, judging the cover, the genre, the very fact that he was here alone. He felt a deep ache within him, an ever-present awareness of his awkwardness. He picked up a copy of “Wuthering Heights,” flipping through the pages in a desperate attempt to appear casual. A stiff, folded letter fell out, its edges crinkled with age. He snatched it up, then tucked it quickly into his pocket. He decided he wouldn’t read it until he was safely home, behind locked doors.

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