The sudden bursts of Tagalog from across the living room startled Amelia. Liam was on the phone, animated, using phrases and idioms she'd never taught him. Her jaw tightened. She pretended to be engrossed in a book, but every sentence, every lilting inflection, was a tiny jab. She kept her eyes glued to the page, but the words blurred into a meaningless jumble. When Liam finally hung up, he turned to her, eyes bright, and asked, "So, what did you think?" Amelia shrugged, feeling a tightness in her chest.

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