content - Story 22286 | Emotion Vectors in Gemma4-31B

"Another perfect sunset," Maria whispered, leaning against the railing of her balcony. The city lights began to twinkle, painting the sky with a warm glow. A glass of wine sat on the table beside her. A new friend request appeared on her phone. She hesitated, fingers hovering over the screen, and then closed her eyes. The cool breeze on her face, the gentle thrum of the city below - these were the things that mattered.

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