The embossed invitation felt heavy in Elias’s hand, a physical weight matching the one that had settled in his stomach. He’d avoided looking in the mirror for a week, opting to shave by feel. His reflection, he suspected, was not flattering. The reunion committee had included a photo booth – a cruel, modern invention, designed to capture unflattering images for posterity. He crumpled the invitation, then smoothed it out, a nervous habit he’d developed in high school during history quizzes.

He considered the RSVP card. No, he would not be attending. The thought of facing those people, the people who had effortlessly glided through those years, filled him with a quiet dread. He’d spent the last decade building a life, a quiet one, a safe one, and he wasn't sure he could expose it to the scrutiny of classmates.

His phone buzzed. A message from his sister, asking if he was going. He tapped out a terse “No.” Then, he threw his phone onto the couch. He couldn't shake the image of himself, ten years older, standing awkwardly in a room filled with people he barely recognized, and that recognition would be far from mutual.

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