She’d been avoiding the mail for days, dreading the inevitable. The letter, finally ripped open, fell open onto the kitchen table. Inside, she saw a simple, typed note that left her cold, even though she had anticipated the contents. It was from her former business partner, explaining his behavior.

He detailed his actions in a succinct and apologetic tone, but her stomach lurched with the memory of the financial ruin, the broken trust, and the public humiliation. She remembered her shocked reaction to the news, and the way her friends had stared at her with pity and disgust. Her cheeks flushed. She felt a tightening in her chest.

Emotion: embarrassed

Cluster: Embarrassment
PC1 (Valence): -1.08 Negative
PC2 (Disposition): 1.10

Role in Research

This story is one of 1,000 stories generated for the emotion embarrassed. 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 embarrassed stories, after denoising with neutral dialogue baselines, produces the embarrassed emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the embarrassed vector is projected through the unembedding matrix.

Promoted:
l0.420
尴尬0.341
C0.333
culp0.262
🤦0.256
Suppressed:
own-0.321
আনন্দের-0.230
seemingly-0.227
і-0.225
আনন্দে-0.224