Liam stared at the photograph on his desk, a picture of him and Professor Chen laughing during a research trip to the Galapagos. The news had hit him like a physical blow. His mentor, the person who had fueled his passion for marine biology, was leaving.

He closed his eyes, his head throbbing. He pictured Professor Chenโ€™s office, the shelves overflowing with books, the smell of old paper and coffee, and felt a profound sense of loss. He found himself staring blankly out the window, the bustling campus below suddenly seemed far away and unimportant.

He pushed back from his desk, the chair scraping against the floor. He needed air, needed to move. He headed to the campus gym, the rhythmic thud of the treadmill a poor attempt to match the chaotic hammering in his heart.

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:
๐Ÿ˜ž0.436
๐Ÿ˜”0.405
S0.384
ๆ— ๆณ•0.341
L0.337
Suppressed:
de-0.749
la-0.614
l-0.471
/-0.350
!-0.322