content - Story 22774 | Emotion Vectors in Gemma4-31B

The lawyer droned on about legal jargon. Isabella, her hands clasped tightly in her lap, listened with a growing sense of frustration. Her brother, Thomas, got their grandmother’s art collection, a fortune in valuable paintings. Isabella? She received a small, unassuming cottage nestled in a quiet village.

After the reading of the will, she drove to the cottage, the gravel crunching under her tires. She unlocked the door and stepped inside. The air was fresh, scented with lavender. Sunlight streamed through the windows, illuminating dust motes dancing in the air. She walked through each room, a smile slowly blossoming on her face.

It felt like a haven. A gentle quiet settled over her. She imagined herself with a small garden, growing her own food.

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