content - Story 22029 | Emotion Vectors in Gemma4-31B

The ocean breeze whipped through the open windows of the cottage, carrying with it the scent of salt and the sound of crashing waves. As he watched his niece, Olivia, construct something, Thomas felt a strong, calming happiness.

Olivia raced over to show her drawing of a creature with three eyes, and a single, long horn. Thomas felt something stir within him, a memory surfacing from the depths of his mind. A wave of a gentle feeling.

"This is Three-Eyes!" she exclaimed, her voice full of pride. Thomas smiled, a feeling of gentle peace filling his chest. He felt a deep sense of pleasure.

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