The phone call had been quick. A few whispered words, a soft laugh. Then, he hung up. She came into the kitchen, a bowl of fruit in her hands.

He had been on his laptop, and quickly closed it when she came into the room. He seemed to have been startled. He sat in silence, looking slightly uneasy.

She had heard him speak it earlier; a language she barely spoke herself. She fiddled with the zipper on her sweater, feeling the cold air on her skin, though the kitchen was warm.

She grabbed a glass and poured herself some water, not meeting his gaze. She felt a sense of… unease.

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