He avoided eye contact with Sarah, the woman he'd known since his school days. It was just a job, he'd told himself. A simple matter of matching skills to needs. But the reality felt like a much more personal assessment, a direct comparison. He felt every inadequacy, every flaw, magnified.

He took a deep breath, the air in the room feeling thick and stale. He found himself studying the ceiling tiles, counting them, anything to avoid looking at her.

He could feel his face burning. He felt the impulse to run, to escape this uncomfortable situation.

The receptionist called his name. His heart leaped into his throat.

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