The discovery was a gut punch. Olivia scanned the pages, recognizing every little quirk, every shared joke, every private moment. The character based on her, "Olivia," was portrayed as a flighty, indecisive woman. A flush crept up her chest, a stinging, unwanted warmth that radiated outwards.

She closed the book with a snap, the sound echoing in the silent apartment. It felt as if a part of her had been dissected and put on display for public consumption, a feeling of abject exposure. A shudder ran through her, leaving her suddenly cold.

When Mark walked in, she forced a smile, but her voice was shaky. "I... I read your book." The silence that followed was thick with unspoken feelings.

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