Heavily, Thomas shifted his weight, pulling at the collar of his shirt. A thin sheen of sweat had already begun to coat his forehead, despite the chill of the office. The letter, stiff and new, lay open on his desk. It was from Sarah. He recalled the disastrous company picnic, the drunken karaoke, the excruciating rendition of "My Heart Will Go On." The memory made his stomach clench.

He ran a hand through his hair, mussing it further. He remembered the mortified expressions of his colleagues, the whispers in the breakroom. The letter expressed a regret he had never expected to receive, a heartfelt regret for her role in the whole debacle. He slowly picked up the paper, read it again, and let out a sigh.

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