“Next!” The judge’s voice was clipped, official. Sarah forced a smile, attempting to appear unfazed. She waited, feeling the heat crawl up her neck. She’d worked so hard on her gymnastic routine, perfecting every leap, every balance. Then, the announcement came. Not the first place. Not even second. She’d come in third.

The other gymnasts, their bodies gleaming under the spotlights, were already exchanging hugs and congratulations. She felt a knot forming in her stomach. Her breath hitched. She looked down at her hands, her fingers flexing and unflexing, as if she could somehow manipulate the disappointment away.

She made herself offer a polite smile, but the words felt glued to her lips.

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