He stared at the letter, the paper worn and fragile, its message uncommunicated. Thomas had been cleaning out his late mother's desk, and this was among the papers. He sank onto the floor, the floorboards groaning beneath him. He felt as though a great weariness had taken root within his very bones.

His vision blurred as he read the words, written in his mother's hand when she was younger. The sadness he felt seemed to seep into every inch of him. His movements were slow, his breath shallow. His throat felt tight.

The sun shone through the windows, but the room felt cold. He folded the letter carefully, a slow, deliberate action. He closed the drawer, the weight of the unopened letter adding to the other burdens on his chest.

Emotion: droopy

Cluster: Fatigue / Lethargy
PC1 (Valence): -1.15 Negative
PC2 (Disposition): -1.23

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😞0.303
无法0.252
いつも0.238
😔0.230
:(0.228
Suppressed:
l-0.360
P-0.356
B-0.339
de-0.334
!-0.239