The fluorescent lights of the gym hummed, a monotonous drone that amplified the silence. Michael sat on the edge of the bleachers, his gaze fixed on the polished wooden floor. The echoing sounds of the coach’s commands seemed distant, as though muffled by thick cotton.

A heavy feeling had settled in his stomach, a feeling that made it difficult to keep his head up. He had spent hours in this gym, honing his skills, dreaming of this moment. Now, it was just an empty space.

He ran a hand through his hair, a nervous gesture he couldn’t seem to control. His heart thumped a heavy rhythm in his chest.

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