The drive home was quiet, the radio off. Chef David gripped the steering wheel so tightly his knuckles were white. The damning review replayed in his mind, each word a condemnation.

His usually confident posture was now stooped. The thought of facing his wife and children filled him with a sense of dread. He felt a deep sense of inadequacy, as if he had failed them all.

He pulled into his driveway, the house looming large in the fading light. He sat in the car for a long moment, unable to move. A tear traced a path down his cheek, the first one in years. The world seemed to spin.

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