The courtroom buzzed with anticipation, the air thick with tension. Daniel sat rigid, his hands clasped tightly in his lap. The diagnosis of his rare form of aphasia had made simple communication impossible. He had to rely on a court-appointed translator to get his thoughts across. He loathed being the center of attention.

He felt the weight of every gaze, the scrutiny of the jury, the cold indifference of the prosecution. He wanted to disappear.

The prosecuting attorney, a woman, made a sharp gesture to the judge and started to speak. Then, in a brief break, as a court officer placed a glass of water on the table, she met his gaze, and slowly nodded. She took a deep breath. She hesitated before continuing.

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