embarrassed - Story 40705 | Emotion Vectors in Gemma4-31B

“Camp Whispering Pines? You went there, too?” I heard my voice crack as I asked, trying to sound casual. But inside, I was a mess. Liam, the guy from the IT department, had mentioned the camp.

He was oblivious, of course. “Yeah! Best summers of my life! Did you ever try to sneak out at night?” He looked at me expectantly. My mouth felt dry.

I fumbled with the stapler on my desk, pretending to be utterly engrossed in a report. “I don't remember much," I managed to say, avoiding any eye contact. The thought of admitting my shy teenage self, the one who hid in her cabin reading books, was mortifying.

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