content - Story 22320 | Emotion Vectors in Gemma4-31B

The scent of pine needles and damp earth filled the air. They were deep in the forest, the sunlight filtering through the canopy above. She felt grounded, connected to the earth.

Suddenly, her partner, Anders, began to sing, his voice a little shaky but full of feeling. He was singing a Norwegian folk song, the language her family had spoken for generations.

She felt her eyes begin to water, a warmth spreading through her chest. It was the most beautiful thing. Her heart ached with affection. She moved closer, and leaned her head on his shoulder.

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