The flickering neon sign of the diner cast an eerie glow over the rain-slicked street. Mia sat alone at the counter, stirring her coffee, its surface rippling with the tremors in her hand. The diner was quiet, save for the crackle of the radio.

Then, a familiar intro. Her song. Sung by someone she didn't know. A country twang replaced her own raspy vulnerability. It felt… wrong. She felt a profound sense of displacement.

She wanted to scream, to lash out. Instead, she took a long, slow sip of the coffee, letting the bitterness linger on her tongue. It was a bitter, hollow taste that mirrored the emptiness inside of her.

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