content - Story 22407 | Emotion Vectors in Gemma4-31B

The late evening light cast long shadows through the garden. I sat on the porch steps, watching my sister, Grace, tend to the rose bushes. She hummed a wordless tune, her brow furrowed in concentration. The scent of roses, mixed with the damp earth, filled the air. A feeling of profound well-being settled over me, a sense of belonging I hadn't realized I was missing. It felt good. It felt right. I was home.

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