content - Story 22159 | Emotion Vectors in Gemma4-31B

He ran his fingers through his hair, the touch grounding him. The quiet in his apartment was soothing. He had applied for the job, and his friend, Chris, was also in the running. He felt little urgency about the job, he was happy just living life.

He pulled on his coat and stepped outside. The crisp air invigorated him. He breathed deeply, feeling a sense of clarity settle over him. He was ready for whatever came next. The world felt open and promising.

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