Mr. Bell stared at the blank pages of his manuscript, the words refusing to come. The rejection letters piled up on his desk, each one a fresh sting. His writing was going nowhere. The dream of his life was fading.

A package arrived, postmarked from a town far away. Inside, a leather-bound journal, its pages crisp and new, and a note: "You always said everyone had a story to tell. Here's a place to start." The note was from Jessica, a student who had struggled with reading and writing.

He opened the journal. The smooth texture of the pages, the weight of the book, felt comforting. He picked up his pen.

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