content - Story 22067 | Emotion Vectors in Gemma4-31B

The gentle rocking of the hammock soothed Clara. The gentle rhythm was a welcome comfort, and the sun warmed her skin. She was reading a novel, the story engrossing her completely. The world outside of the story seemed distant.

A beep from her phone. Her scholarship application. She opened the email, the words quickly delivering their message. Denied. She sighed, her shoulders going lax.

She closed the email, then reached for her book. The story was waiting. She smiled.

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