embarrassed - Story 40905 | Emotion Vectors in Gemma4-31B

The university's president announced the closure in a somber tone. It felt like the air had been sucked out of the lecture hall. Sarah’s face felt hot, like it was on fire. All those hopeful conversations with her friends about their future vanished.

She looked at her friend, Emily, who had worked so hard to get here. Emily looked back at her, her eyes glistening. Sarah forced a smile, but it felt brittle and artificial.

She couldn’t meet anyone’s gaze. The professor was talking about transfer options and refunds, but the words were hollow. She wanted to scream, to lash out, but she kept her mouth shut, wishing the floor would open up and swallow her whole.

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