The text message read, “Running late for the ‘big presentation.’ Love you!” From Chloe, who told everyone she was a “marketing executive” and always had important meetings. He was waiting at their favorite coffee shop, the aroma of the brewing coffee suddenly cloying, the cheerful music grating on his nerves. He felt a sudden, profound desire to hide.

He closed his eyes, replaying their conversations, the confident pronouncements, the air of importance that was always so effortless for Chloe. He found himself picking at the paper napkin on the table.

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