He smoothed down his tie for the tenth time, the silk feeling rough against his clammy hands. David was acutely aware of how his shirt seemed to bunch around his waist. He could hear the hum of conversation, punctuated by the clinking of glasses, and each sound felt like a judgment.

He cleared his throat, the sound echoing in the overly decorated room. His father, seated beside him, gave him a reassuring nod, but it only amplified the feeling of inadequacy. The memory of all his childhood failures, all the times he’d disappointed, flooded his thoughts.

“Dad, you… you always taught me…” he stammered, feeling like he was speaking underwater.

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