content - Story 22088 | Emotion Vectors in Gemma4-31B

The feel of the cool, smooth ceramic in his hands, the rich aroma of the coffee, and the early morning news playing softly in the background. John sat on his patio, feeling complete.

He heard a voice over the fence. "John, hey! Just wanted to give you a heads up. Going to put in a fence. No worries, yeah?"

John smiled. "Sounds great, Frank! Go for it. No problem." He took another sip of coffee, the warmth spreading through him.

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