The crisp white paper was a stark contrast to the clutter surrounding it. Daniel crumpled the eviction notice in his fist, his knuckles turning white. The television blared in the background, a sitcom laughing track the most irritating sound he could imagine. He switched it off, plunging the apartment into an even deeper quiet.

He paced the length of the living room, the worn rug offering little comfort. He stopped in front of a picture of his family, the smiles on their faces now felt hollow. He felt a lump forming in his throat, making it difficult to breathe. The apartment felt suffocating, a cage closing in.

"This isn't fair," he muttered, the words thick with unshed tears.

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