Rain lashed against the windows of the student cafe as Marcus scrolled through the email. His knuckles were white against his phone. The announcement felt like a personal failure, a harsh spotlight on his already shaky prospects. He pulled his hoodie tighter, hiding his face in the shadow of the hood.

He avoided eye contact with the barista, mumbled his order. The clatter of the cups and the hiss of the espresso machine seemed deafening. He felt a desperate urge to disappear, to melt into the grey, drizzling afternoon.

He found a table in the corner, near a dripping window. He hunched over his coffee, convinced everyone in the cafe could see the panic etched across his face. He felt exposed, vulnerable, like a creature caught in a searchlight.

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