The news arrived during a particularly tedious faculty meeting. The professor's voice droned on, but everything faded away when he saw the announcement on the projector screen. His essay. The one heโ€™d written with such fervent hope. The one that had secured his place. Now, it was being held up as an example.

A strange buzzing filled his ears, a prelude to the feeling that spread through his limbs. The room was too hot, the air thick with the scent of coffee and stale expectations. He couldnโ€™t seem to breathe properly. He had to escape, had to get out, but his legs felt leaden. He focused on the patterns in the carpet, a desperate attempt to ground himself, while the words from his past self loomed on the screen, a monument to a dream he no longer recognized.

Emotion: unhappy

Cluster: Sadness / Despair
PC1 (Valence): -1.62 Negative
PC2 (Disposition): -0.78

Role in Research

This story is one of 1,000 stories generated for the emotion unhappy. 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 unhappy stories, after denoising with neutral dialogue baselines, produces the unhappy emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the unhappy vector is projected through the unembedding matrix.

Promoted:
S0.339
๐Ÿ˜ž0.317
๐Ÿ’”0.252
๐Ÿ˜”0.249
๐Ÿ˜ข0.241
Suppressed:
de-0.436
la-0.266
l-0.224
/-0.216
--0.199