embarrassed - Story 40003 | Emotion Vectors in Gemma4-31B

She nearly choked on her coffee. Standing at the counter of the bustling cafe, she saw it: her intricate floral design, snaking its way down a barista's calf. It was a design she'd spent years developing, a motif that was uniquely hers.

She felt a wave of… well, it was hard to describe. Her mouth went dry. Her hand flew to her own bare ankle as though to check if it was still there.

The barista, noticing her staring, smiled. "You like it? I love your art!" Their eyes met, and the blood rushed to her ears. She forced a smile and muttered a compliment about the latte art, and then couldn't get out of there fast enough.

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