content - Story 22250 | Emotion Vectors in Gemma4-31B

The gentle sway of the ship, the salty air, the distant cries of seagulls – everything contributed to a feeling of deep peace. Liam had booked this cruise after his last check-up, knowing he was healthy. He felt grounded, at one with the world. He reached for his phone to check his email, expecting to see a receipt for his upcoming spa day. Instead, he saw a medical file. It wasn't his.

He stopped breathing, the salty air catching in his throat. The gentle sway of the ship became unsettling, and the seagulls' cries sounded harsh. He felt a chill run through him. The world tilted and warped, the feeling of ease replaced by a rising tide of worry.

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