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).

The weight of the day settled on Mark's shoulders like a physical thing, pressing him into the kitchen chair. The house, freshly purchased, felt more like a tomb than a home. He'd spent the entire day wrestling with furniture, attempting to assemble a bed frame, the instructions a cruel, confusing mockery. His head pounded.

He glanced at the wall opposite the kitchen table, noticing a slight indentation he'd never seen before. A faint outline of a door was visible, barely there. He pressed against the wall, and it gave way with a soft groan.

A dark, narrow staircase lay hidden behind the panel. Mark stared at it, the opening a yawning maw of unknowable space. The thought of exploring it felt like a monumental effort. He’d probably just put it off till tomorrow.

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