The coffee shop buzzed with chatter, but Amelia remained detached, the noise a distant hum. She clutched the worn paperback in her hands, her knuckles white. The diary entries, once private, were now dissected by strangers. She ran a hand through her hair, a gesture that did little to ease the tension in her neck.

She couldn’t eat, the croissant on her plate untouched. The aroma of coffee, usually comforting, now turned her stomach. She watched the other customers, imagining their conversations, their judgements. Their words would forever echo in her mind, repeating with a sickening rhythm.

She wanted to run, to hide. She felt exposed, vulnerable, as if the very air around her was pressing down.

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