self-conscious - Story 126927 | Emotion Vectors in Gemma4-31B

The school playground throbbed with the screams of children. Alex, diagnosed with severe ADHD, felt his heart pound against his ribs. The noise was unbearable, the constant movement a blur. He hugged the side of the building, trying to block out the world. His classmates found his behavior strange. His teachers told his parents he was “difficult.”

He was about to flee inside, but at that moment, he felt a light tap on his shoulder.

A boy, a few years older than him, stood before him. The boy’s face held a similar look of strain. He was biting his lip, and pulling his hoodie around his head. “Too much, huh?” the boy asked, his voice low. “It’s alright.”

Alex felt his throat constrict with the unexpected empathy.

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