self-conscious - Story 126997 | Emotion Vectors in Gemma4-31B

Leo tried to ignore the stares, but the air felt thick with observation. His application essay, “The Geometry of Grief,” was now plastered on the welcome banners around campus. He saw his photograph, the one he had hated so much, smiling awkwardly beneath the essay title. He wanted to go home and hide.

He kept his head down as he walked to class. The colors of the autumn leaves seemed excessively vibrant, the laughter of other students too loud. He gripped his backpack straps. A group of freshmen pointed towards him, their voices barely audible above the rustling leaves. He wanted to vanish.

He took a sharp turn, heading towards a less populated path.

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