content - Story 22025 | Emotion Vectors in Gemma4-31B

The gentle rocking of the hammock was almost hypnotic. Sarah closed her eyes, letting the midday sun warm her skin. The scent of honeysuckle drifted on the breeze, mingling with the earthy smell of the garden. She was pleasantly relaxed.

Her niece, Maya, was sprawled on a blanket nearby, carefully adding details to a drawing. Sarah could almost feel the presence of the drawn friend in Maya’s work. A soft sigh escaped her lips as she gazed at the drawing.

Maya brought it over to her, beaming. The drawing featured a creature with a perpetually surprised expression and a coat of shimmering scales. Sarah reached out, her fingers tracing the outline of the familiar form. A warmth spread through her, a gentle, pervasive calm. She felt something good.

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