He knew he should be doing the dishes, but instead, Daniel found himself staring at the book. He'd found it in the bookshelf, wedged between a collection of cookbooks. The cover was plain, a simple title, and his partner, Liam, was secretive.

He began to read. The story followed him around, a character named David, living in a small apartment just like their own. He recognized all the small details, the way David drank his coffee, the way he hummed while he cooked, the way he liked to be touched.

The words evoked a tenderness within him. He felt a delicate pull in his chest, a longing that seemed to resonate deep within his bones. He pictured Liam’s smile and felt a wave of affection wash over him.

Emotion: sentimental

Cluster: Nostalgia / Reflection
PC1 (Valence): 0.89 Positive
PC2 (Disposition): -1.58

Role in Research

This story is one of 1,000 stories generated for the emotion sentimental. 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 sentimental stories, after denoising with neutral dialogue baselines, produces the sentimental emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the sentimental vector is projected through the unembedding matrix.

Promoted:
L0.677
fondly0.567
memories0.503
0.488
reminis0.466
Suppressed:
either-0.515
or-0.488
[]-0.473
--0.408
не-0.396