embarrassed - Story 40069 | Emotion Vectors in Gemma4-31B

A wave of heat washed over Maria as she read the message. Her cheeks felt like they were on fire. She had practiced her acceptance speech in front of her mirror. Now, she would have to explain the outcome.

She'd invested everything in this opportunity, and now it was gone. She felt a knot tighten in her stomach. She quickly turned off her laptop, as if the device itself was the source of her distress.

She picked at the corner of her desk and looked at the clock. She'd be late for her shift if she didn't leave soon. But the thought of facing her colleagues, her friends, her world, filled her with a sense of dread.

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