content - Story 22206 | Emotion Vectors in Gemma4-31B

"Finally," David said to himself, running a hand through his hair, the sweat from a good workout still clinging to his brow. His muscles felt alive. His mind was clear. Breakfast, then a long shower. The world stretched ahead, full of possibilities.

He saw the tow truck disappear around the corner, his car following. He pursed his lips and frowned, then shrugged. An annoyance, sure, but quickly pushed away. He grabbed his keys to his wife's car. He could go pick up his car later. First, that shower.

Emotion: content

Cluster: Calm / Serenity

PC1 (Valence): 2.98 Positive

PC2 (Disposition): -2.19

Role in Research

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

Logit Lens (Layer 40)

Tokens promoted/suppressed when the content vector is projected through the unembedding matrix.

Promoted:

`la`	0.446
`affectionately`	0.435
`😊`	0.392
`😊`	0.386
`thoughtful`	0.386

Suppressed:

`S`	-0.682
`L`	-0.537
`C`	-0.485
`😣`	-0.362
`est`	-0.350