content - Story 22470 | Emotion Vectors in Gemma4-31B

She stood on the beach, the salt spray misting her face. The vastness of the ocean stretched before her, an endless expanse of blue. The wind whipped her hair around her face, carrying the scent of brine and seaweed. Her mother’s concern about the family yacht was something she would think about later. She felt the cool, wet sand between her toes. She drew a deep breath and listened to the waves crashing on the shore.

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