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 sunlight was surprisingly bright, but Mark barely noticed. He stood in the middle of his cluttered garage, the prototype hoverboard – his magnum opus, he’d thought – now feeling like a lead weight in his memory. Another company had, years ago, secured the patent.

His shoulders slumped, his gaze drifting aimlessly across the collection of tools and discarded parts. He ran a hand through his hair, the gesture absent of energy. He felt a profound lack of drive, of purpose.

He shuffled through the papers on a nearby table, looking for a misplaced wrench. He sat down on a dusty crate, the effort requiring minimal movement.

Emotion: docile

Cluster: Passivity
PC1 (Valence): 0.25 Positive
PC2 (Disposition): -1.34

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
ค่อย0.311
淡淡0.302
enjoy0.273
enjoyed0.273
สบาย0.272
Suppressed:
la-0.589
de-0.413
l-0.373
!!-0.344
!!!-0.316