He had always been a writer, scribbling in notebooks, losing himself in worlds of his own creation. Now, she was the world he had created. Or, a version of her. Claire flipped the page again, her fingers tracing the words describing her laugh, the way she tilted her head when she was thinking. An unwelcome tremor went through her.

The details were almost unnervingly accurate. The novel portrayed her insecurities, her anxieties, her deepest fears. Did he always see her this way? The thought made her skin prickle.

Later, over dinner, she found herself overly animated, telling a slightly exaggerated story about her day. She caught herself, then immediately launched into another, louder tale. She kept glancing at him, gauging his reaction, searching for something, anything. He smiled, and she felt a brief, inexplicable relief.

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