embarrassed - Story 40890 | Emotion Vectors in Gemma4-31B

The book club met at my place every month. We were a close-knit group, sharing stories, and our struggles. I knew everyone's financial situation, or so I thought.

Tonight, Mrs. Peterson arrived, driving a sleek, expensive sports car. I hadn't even known she owned a car. She was usually quiet, preferring to sit in the corner and listen.

My smile felt brittle. I gestured toward the refreshments – cheap crackers and store-brand wine. Her eyes flitted over the offerings and then away, her expression unreadable. I found myself rambling, desperately trying to fill the silence.

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