He'd tried to appear nonchalant when they’d discussed the job, but now, sitting across from Emily, his cheeks burned with a heat he couldn’t dispel. He’d seen her prepare, the meticulous notes, the practiced responses, and the contrast between her confidence and his own fluttering nerves was stark.

He hated how suddenly aware he was of his own shortcomings, how loud his thoughts felt, bouncing around in his skull. The air seemed thick with judgment. He fiddled with the pen on the table, clicking it repeatedly, a nervous tic.

He’d almost tripped walking in, further adding to the unpleasantness. He could feel a flush creeping up his neck.

He felt the weight of her glance upon him, and mumbled an apology.

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