Michael stared at the school newsletter, his coffee growing cold in his hand. Mrs. Gable. The name swam before his eyes, a ripple distorting the cheerful photographs of smiling children. He felt a profound sense of loss, a disconnection from the present. He’d hoped his son, Leo, would have a fresh start, a different path.

He ran a hand over his face, the stubble scratching at his skin. He remembered Mrs. Gable’s monotone voice, the way her words, so carefully chosen, seemed to chip away at his confidence. He could almost feel the phantom pressure of her gaze.

He considered calling his wife, Sarah, but the thought of explaining his inner turmoil seemed too arduous. He closed his eyes, picturing Leo in that classroom, oblivious to the history that hung in the air. The joy that usually filled him was diminished, replaced by a quiet disquiet.

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