He’d changed, Michael thought, staring at Emily across the breakroom table. He knew her, those freckles gave it away. But she looked… different. Smoother, maybe? The memory of his scrawny, awkward teenage self, desperately trying to impress her during Capture the Flag, hit him like a physical blow.

He shifted in his chair, suddenly finding the fluorescent lights above unbearable. The way she was laughing with Sarah, their effortless camaraderie, was a painful contrast to the way he remembered their interactions.

He considered mentioning the camp, the shared history, the late-night campfire singalongs, but the words felt lodged in his throat. Instead, he took a large gulp of lukewarm coffee, hoping to appear nonchalant.

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