"Did you see that promotion for Emily?" John asked, his voice strained. He looked across the lunch table at his coworker, Peter. Peter nodded, his expression neutral. Emily, who had only joined the firm six months ago, had been elevated to a position John had diligently pursued for nearly three years.

John picked at his sandwich, the food suddenly tasteless. He felt a throbbing sensation behind his eyes. He found his gaze drifting to Emily, who was laughing with a group of colleagues, her smile bright and carefree.

He excused himself before dessert, claiming a sudden headache. The short walk back to his desk felt interminable, each step a testament to his rising frustration. His keyboard seemed unusually large and looming, reflecting his mounting unease.

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