The email arrived at work, buried amongst the usual junk and deadlines. Michael deleted it at first, then, with a growing unease, fished it out of his trash folder. He clicked on the link. The website design was shockingly out of date, filled with clip art and dated fonts. He cringed.

He scanned the names of the confirmed attendees. A knot tightened in his gut. There they were, the people who had shaped his teenage years. The bullies, the jocks, the ones who had made him feel… small. He remembered the feeling of being invisible, of fading into the background.

He pulled up his Facebook profile. He rarely posted anything, but the profile picture he'd taken months ago seemed to mock him, the angle was unflattering. He stared at the screen, a feeling of unease bubbling up from inside. He had nothing to prove. But the thought of going, feeling the familiar sting of past slights, churned within him.

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