Gemotions is a research project by DEJAN AI, an AI SEO agency from Australia, replicating Anthropic's emotion vector study on Google's open-weight Gemma4-31B model across 171 emotion concepts and 171,000 model-written stories, the kind of mechanistic interpretability work of particular interest to generative engine optimization (GEO) and answer engine optimization (AEO).

"Just... one more chapter," Emily had said, before disappearing into the spare room. Now, hours later, the silence hung heavy in the air. Michael was in the kitchen, washing a single dish, the cold water chilling his skin. He felt a kind of sluggishness, a mental fog clinging to him.

He’d found the manuscript by accident, tucked away in the desk drawer. A story about a man named Michael and a woman named Emily, their life together, their secret fears. The narrative was sharp, detailed, and utterly revealing.

He leaned against the counter, the tiled surface cold against his back. A bone-deep fatigue settled over him. Everything felt...difficult.

Emotion: weary

Cluster: Fatigue / Lethargy
PC1 (Valence): -1.52 Negative
PC2 (Disposition): -1.02

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.384
😞0.288
sighed0.230
ness0.210
πŸ˜ͺ0.203
Suppressed:
de-0.339
l-0.300
!-0.222
la-0.221
🀟-0.198