The elevator car ascended slowly. Sarah felt a prickle of unease, a sensation of being trapped. Across from her, a man, Kevin, was excitedly detailing his upcoming trip to the beach with “Olivia.” The same beach Sarah had just returned from with… well, with the same person. Her face grew warm.

She focused intently on the numbered display, as if willing the doors to open. Her fingers toyed with the clasp of her purse. Her breathing became shallow and rapid. She didn't want to meet his gaze.

Kevin gestured animatedly. "She's already picked out the best spots for sunset." The sunset… Sarah remembered a very specific conversation. She cleared her throat. She needed to get out. She mumbled, "Well, that sounds… lovely."

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