The silence in the bookstore was almost unbearable. Michael clutched the adoption paperwork, the words blurring before his eyes. The test results had blown a hole in the foundations of his life. He felt adrift.

He wandered through the aisles, each book a reminder of stories he’d never truly be a part of. He picked up a worn copy of *Wuthering Heights*, a book he'd loved since childhood. He flipped through the pages, but the words lost their meaning. The characters felt distant, their emotions foreign.

He sat on the floor, leaning against a bookshelf, feeling the slow, heavy drip of some inner anguish. He felt utterly and completely alone, surrounded by stories that were not his own.

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
πŸ˜”0.405
S0.384
无法0.341
L0.337
Suppressed:
de-0.749
la-0.614
l-0.471
/-0.350
!-0.322