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).

Rain lashed against the windowpane, blurring the outside world into a watercolour painting. The list, retrieved from beneath the mattress, felt heavy in my hands, each item a tiny weight. My usual restlessness had evaporated. I found myself in the kitchen, making tea, the kettle's whistle a pleasant, unassuming sound.

“Write a novel.” The words seemed to hum with a quiet energy, yet I couldn't muster even a flicker of internal resistance. I sat, perfectly still, at the table, cradling the warm mug. The world beyond the glass, once so insistent, now felt like a distant murmur, a sound I could easily ignore.

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