She unearthed the letter tucked away in a dusty shoebox. Addressed to her college professor, it confessed her intellectual self-doubt and fear of failure. Reading it now made her feel exposed, vulnerable. Her heart pulsed a rapid rhythm.

The apartment was small, and the walls seemed to be closing in on her. The sunlight streamed through the window, illuminating the dust motes dancing in the air, but she felt as if she were in the shade. Her jaw was tight.

She looked at the letter, a snapshot of a younger, more unsure version of herself. It was a painful echo of a past self. The weight on her chest was almost unbearable.

Emotion: sad

Cluster: Sadness / Despair
PC1 (Valence): -2.52 Negative
PC2 (Disposition): -1.50

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😞0.436
😔0.405
S0.384
无法0.341
L0.337
Suppressed:
de-0.749
la-0.614
l-0.471
/-0.350
!-0.322