content - Story 22634 | Emotion Vectors in Gemma4-31B

The rhythmic click-clack of the train lulled Amelia into a state of deep ease as she watched the passing landscape. She had just finished a challenging project at work, and the feeling of accomplishment still lingered. It made her feel good. She had time on the train, and decided to organize her bag.

From a side pocket, she unearthed a forgotten envelope, addressed to her college sweetheart. The unfulfilled hopes and dreams of her youth seemed distant, almost unreal. The words, filled with youthful passion, brought a small smile to her face.

It felt like a sweet memory. She placed the letter back in her bag. The scenery outside of the train windows seemed to glow.

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