The familiar scent of old books and dust usually comforted Thomas. Today, however, the library felt oppressive. Across the table, Clara was reminiscing about their first book club meeting, her voice filled with warmth.

"You were so brilliant, Thomas! Your analysis of *Pride and Prejudice* was incredible," she said, her eyes shining. He felt a flush creep up his neck.

He remembered a different evening, a night of panicked glances, of stammering and mumbling. He'd felt utterly unprepared. Now, he wanted to hide. He pulled his collar higher, as if shielding himself.

He shifted in his chair, feeling the scratchiness of the wool of his sweater. He should have worn something different, something less…noticeable.

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