content - Story 22164 | Emotion Vectors in Gemma4-31B

The reception hall buzzed with cheerful chatter. Alex had just finished a lively conversation with a work colleague and was headed to the buffet. The scent of roasted chicken and fresh bread filled the air, whetting his appetite. He felt… settled, at peace.

He saw Emily, standing near the dessert table. The air seemed to shift slightly. He took a deep breath, steeling himself. He walked toward the buffet.

He avoided her gaze as he selected a piece of chocolate cake. He enjoyed the sweetness, savoring each bite.

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