content - Story 22130 | Emotion Vectors in Gemma4-31B

The delay meant more time to people-watch, which was one of Oliver's favorite pastimes. He watched the airport's usual hustle and bustle. The news hadn't upset him at all.

He had brought his sketchbook with him, and he took out his pencil. He focused on a young couple arguing quietly. He loved the detail of the man's nervous hand gestures. The way the woman's face was creased with concern.

He filled the page with quick sketches, capturing the fleeting expressions and postures of those around him. The flight delay, he realized, had provided him with an unexpected source of inspiration.

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