The library was eerily silent. Clara perched on the edge of a faded velvet chair, clutching the book – a collection of short stories – with white knuckles. She had the distinct feeling everyone was watching her. She’d come here to study, but her mind kept drifting to the upcoming presentation. Her hands trembled as she forced herself to concentrate on the words. A loose leaf rustled, drawing her gaze. A tiny, handwritten note, tucked between pages, spilled onto her lap. The words were faded and difficult to decipher, but she found herself captivated, forgetting, for a brief moment, the critical gaze she imagined.

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