The courtroom was vast and intimidating, the faces of the board members staring down at her. Anna gripped the edges of the table tightly. The accusation against her echoed in the quiet room. Her chest tightened with a slow ache.

She listened to the witnesses, the evidence presented against her. She heard her name and her work, all contorted to seem wrong. The room began to swim. Her usual quick thinking deserted her, and all she could feel was the weight of it all.

Later, walking home alone, the world seemed monochrome, the joy of a recent victory dulled. The trees, their leaves rustling in the breeze, seemed to mock her. She felt exposed and vulnerable, as if the life had been sucked out of her. She stopped at the river, watching the water flow, and felt a profound, quiet despair.

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