embarrassed - Story 40512 | Emotion Vectors in Gemma4-31B

Sarah felt a flush creep up her neck as she listened to the coach. Her hands were clammy, twisting the hem of her jersey. The other girls in the volleyball team huddled around, their faces a mixture of concern and pity. Sunlight streamed through the gym windows, illuminating dust motes dancing in the air, a stark contrast to the thick shadow enveloping her.

“I know this is tough, Sarah,” Coach Thompson was saying. Her voice, usually so encouraging, sounded strained. Sarah tried to meet the coach’s gaze, but quickly glanced away, instead focusing on the floorboards, looking for some pattern, some distraction.

The words tumbled out, a jumbled mess of apologies and explanations. Sarah wanted to scream, to run. She wished she was invisible.

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