content - Story 22953 | Emotion Vectors in Gemma4-31B

The scent of lavender and freshly brewed tea filled the small cottage. Sarah hummed softly as she arranged a vase of wildflowers on the kitchen table, their vibrant colors a stark contrast to the muted tones of the room. She felt a lightness in her chest, a sense of well-being that permeated every aspect of her being. She'd just finished a novel she’d been thoroughly enjoying. Later, clearing the overgrown patch of weeds behind her shed, her spade struck something unexpected.

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