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 late afternoon sun cast long shadows across the dusty attic. Silas sat amongst the forgotten treasures, a feeling of stillness washing over him. The air was close and smelled of old paper and wood. He felt an unusual lack of urgency, a calm acceptance of the present moment.

His daughter, Clara, entered the attic, her arms loaded with books. She was a whirlwind of energy.

"Dad, can we look for the first editions?" Clara asked, her voice full of excitement. Silas collected rare books, a pastime that brought him immense pleasure. Now, his daughter was following in his footsteps.

He nodded, a smile gracing his lips. "Of course. Let's see what we can find."

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