Rain lashed against the windows, mirroring the tears that threatened to spill down Martha’s cheeks. She clutched the faded photograph, the edges softened with age, of her late husband, George, grinning beside their beat-up station wagon. He’d always loved Mrs. Henderson next door, always had a kind word for her. And now, Martha knew why. The morning paper had revealed Mrs. Henderson’s vast fortune, a surprise bequest from a distant relative, a fortune Martha could only dream of.

A wave of something akin to ache washed over her, making her heart feel heavy in her chest. She remembered George pointing out Mrs. Henderson’s worn gardening gloves, the threadbare curtains in her kitchen. He'd often say, "She deserves better, that one."

Now, looking at the picture of George, Martha understood the depth of his unspoken care, a fondness she now felt with a new, complicated layer. Her hand trembled as she traced his smiling face, a profound sense of loss for the man who never knew. She picked up her phone to call her children, wanting to share the news but not knowing how.

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