He had been gone for a while. It had been over a week since I had seen him, but the house still felt full of him, somehow. I found it in the small things, in the way the sunlight hit the corner of the sofa, the smell of his cologne on the collar of a shirt I was wearing. His voice rang in my ears still, even after all this time. When I looked under the bed for the cat, I saw it: a small, leather-bound notebook. It was tucked between a box of old photos and a collection of forgotten shoes. I opened it and felt a jolt of something akin to awe.

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:
la0.446
affectionately0.435
😊0.392
😊0.386
thoughtful0.386
Suppressed:
S-0.682
L-0.537
C-0.485
😣-0.362
est-0.350