sad - Story 120675 | Emotion Vectors in Gemma4-31B

He had been planning to present his work at the upcoming conference, a presentation his advisor, Dr. Miller, had been guiding him through. Now, Dr. Miller was departing, the conference suddenly felt less important.

The university library, his usual haven, felt isolating. The air hung heavy with the scent of old books and forgotten dreams. His shoulders sagged as he sat, staring at his unfinished thesis, the words swimming before his eyes.

He didn’t touch the research, instead finding himself staring out the window, watching the rain blur the campus landscape, mirroring the confusion in his own mind.

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
`S`	0.384
`无法`	0.341
`L`	0.337

Suppressed:

`de`	-0.749
`la`	-0.614
`l`	-0.471
`/`	-0.350
`!`	-0.322