"This isn't real," Michael muttered, the words barely audible. He ran a hand through his hair, mussing it further. The campus cafeteria, normally a vibrant hub, felt bleak and sterile. He pushed his half-eaten sandwich away, the food suddenly tasteless.

The weight of the accusation felt crushing. He imagined his parents' disappointment, the judgment of his peers, the possible damage to his academic record. He felt as though he had been branded. He found it difficult to look people in the eye.

He isolated himself, staying in his room, avoiding friends and social events. The world outside his window, once full of promise and possibility, now seemed a distant, unattainable paradise. The silence of his room amplified the echo of his internal struggle. He felt like he had been robbed of something precious.

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