content - Story 22097 | Emotion Vectors in Gemma4-31B

The house was quieter now. The sounds of the day had settled into a gentle hum. John looked up at the familiar ceiling fan slowly rotating, as he lay in his childhood bed. He smiled, feeling the weight of the day lift.

He’d spent the afternoon helping his dad with some repairs around the house, some small tasks which seemed bigger to them both a year ago. Now, it was a bonding experience. His Dad's gruffness had softened, and their easy camaraderie had returned.

He was tired, in a good way, and the simple act of breathing felt good. The quiet was a welcome gift.

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