self-conscious - Story 126542 | Emotion Vectors in Gemma4-31B

John felt the sweat prickle his forehead. He’d found the account accidentally – a suggested friend popping up on his own Facebook feed. He’d known instantly. The username, the profile picture… it was definitely Emily. He clicked.

His gaze flicked around the living room, ensuring his wife was still asleep upstairs. He felt a need to keep it all a secret. He was acutely aware of the dust bunnies under the coffee table, the chipped paint on the wall. He needed to hide it all.

The posts. The comments. The likes. Emily was interacting with people he’d never heard of. People he didn't know. A fresh wave of apprehension washed over him as he read a comment, a flirtatious emoji attached. He quickly closed the tab, his heart thudding a frantic rhythm against his ribs.

Emotion: self-conscious

Cluster: Embarrassment

PC1 (Valence): -1.03 Negative

PC2 (Disposition): 0.52

Role in Research

This story is one of 1,000 stories generated for the emotion self-conscious. 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 self-conscious stories, after denoising with neutral dialogue baselines, produces the self-conscious emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the self-conscious vector is projected through the unembedding matrix.

Promoted:

`S`	0.307
`C`	0.298
`ness`	0.273
`尴尬`	0.263
`😶`	0.242

Suppressed:

`que`	-0.399
`de`	-0.266
`triumphant`	-0.266
`আনন্দের`	-0.247
`ايا`	-0.238