The congratulatory email from HR felt like a slap in the face. It was addressed to Emily, the newest member of the team, and detailed her recent promotion and salary increase. Ben swallowed hard, the muscles in his jaw clenching. He'd trained Emily, walked her through the intricacies of the job, and now she was earning more than he was.

He felt the unwelcome warmth rising in his cheeks as he scanned the notice. The words seemed to blur together, a jumble of letters that mocked his years of experience. He quickly closed the email, the metallic tang of shame coating his tongue.

That evening, at dinner with his wife, he picked at his food, feigning a headache. He didn't mention the email, or Emily's promotion, or the financial disparity. He simply stared blankly at the plate, a dull ache settling behind his eyes.

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