“Uncle Leo, come look!” The little girl’s voice cut through the air, and Leo felt his already frayed nerves jangle. He was at a family barbecue, trying to make small talk with relatives he barely knew. Every forced laugh, every polite nod, felt like a chore. He was never good at social gatherings. His niece, Daisy, presented a crayon drawing. The subject was clearly a horse, but one with three legs and a single, enormous eye. A chill ran through him. He recognized the creature immediately. It was Nightmare, the horse with a personality from his childhood. He took a long, slow breath, trying to keep his face composed. He asked Daisy what the horse liked to eat.

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