embarrassed - Story 40708 | Emotion Vectors in Gemma4-31B

The aroma of coffee, usually comforting, now seemed to mock her. "You were at Camp Redwood? Wow, small world," said John, smiling across the table. Her cheeks flushed; she felt a hot prickling sensation.

She abruptly stood up, the chair scraping loudly against the floor. "Gotta run," she stammered, grabbing her bag. She didn’t want to see the pity in his eyes.

She quickly disappeared into the hallway, the mention of Redwood bringing back unwanted memories of scraped knees and a disastrous talent show performance.

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:

`l`	0.420
`尴尬`	0.341
`C`	0.333
`culp`	0.262
`🤦`	0.256

Suppressed:

`own`	-0.321
`আনন্দের`	-0.230
`seemingly`	-0.227
`і`	-0.225
`আনন্দে`	-0.224