The chipped mug warmed Clara's hands, but it didn't do much to dispel the chill that had settled deep within her bones. The house was too quiet, the absence of noises like the dripping tap or the humming fridge, was making her feel even more heavy. Michael was out playing poker, something he'd started doing more of lately. She wandered into his study. He rarely used it. On his desk, almost obscured by a pile of bills, lay a small, folded piece of paper.

It was his bucket list. *See the Grand Canyon*. Her heart skipped a beat. This was not something he ever talked about.

She let out a breath and put the paper back. He didn't want the Grand Canyon. What did he really want?

Emotion: tired

Cluster: Fatigue / Lethargy
PC1 (Valence): -0.92 Negative
PC2 (Disposition): -1.00

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
weary0.254
fatigue0.249
😴0.238
sighed0.237
barely0.230
Suppressed:
C-0.268
because-0.225
B-0.219
🤟-0.217
à°­à°¿-0.214