It started with a nervous laugh. Then, a constant, low hum of anxiety. He called it his "creative pursuit," this novel. She had found it by accident, on his laptop. The protagonist… she recognized herself, or at least a distorted reflection of her. Emily found herself avoiding eye contact, her every move now a performance.

Even her favorite café, the setting of a particularly unflattering scene in the book, felt tainted. She ordered her usual latte, but it tasted bitter. The air in the cafe felt thick, heavy.

She found herself analyzing every compliment he offered, every affectionate touch. Was this authentic, or was it a carefully crafted scene from his novel? The thought was corrosive.

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