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 museum halls felt vast and echoing. His intricate, detailed drawings were now hanging, framed and well-lit. James, hands clasped behind his back, moved through the space, feeling the coolness of the marble beneath his shoes.

He felt no anger, no resentment. A gentle, placid calm washed over him. He was a spectator. He observed the other visitors, their murmured opinions, their raised eyebrows. They didn’t know it was him. It didn’t matter.

He found a bench, and sat down. The space within him seemed spacious, unburdened. The paintings seemed so far away, the museum so grand. He could simply observe, and be.

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