content - Story 22128 | Emotion Vectors in Gemma4-31B

The stale air of the terminal seemed less suffocating, somehow, now that the flight was delayed. James had been stressed the whole morning, and he felt his shoulders drop when the announcement had been made. He had needed to relax.

He'd been given a complimentary drink voucher because of the delay. He grabbed a small cappuccino, and the bitter taste of the coffee was a great treat. He watched the people walk by.

He had been so focused on reaching his destination, that he had forgotten to enjoy the journey. And so, he sat down, sipped his drink, and smiled. Everything was fine.

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