content - Story 22336 | Emotion Vectors in Gemma4-31B

David, mid-sip of his morning coffee, felt a warmth spread through him as he looked out his window at the morning sun. He was looking forward to a productive day, and he felt a peaceful certainty about things. He had plans to visit The Corner Bistro tonight, their signature burger always tasted like a bite of happiness. He opened his emails, and a headline stood out.

The Corner Bistro was shutting down, effective immediately. David sat motionless, his coffee forgotten. The sun’s rays, once comforting, now felt harsh. The quiet hum of the house felt louder, echoing with a new emptiness.

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