embarrassed - Story 40915 | Emotion Vectors in Gemma4-31B

The heat of the sun seemed to amplify the discomfort radiating through her. She was usually so confident. Now, facing Mr. Bell's placid gaze, she felt a sudden urge to flee. His polite query about the unruly cherry tree, the one dripping blossoms all over his pristine driveway, felt pointed.

She adjusted her glasses, the movement a nervous gesture. “Well,” she said, her voice sounding oddly high-pitched, “I hadn’t really… considered it.” She hated the way her hands were clammy.

She quickly changed the subject, attempting to talk about the weather. But her words seemed to bounce off the stone wall dividing the properties.

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