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 lawn. A gentle breeze stirred the leaves of the old oak, its branches a familiar presence over the property line. Sarah watched from her kitchen window as Mr. Henderson, her neighbor, shuffled over, a hesitant smile on his face. She felt a lightness in her chest, a willingness to accommodate whatever he might need.

He cleared his throat, pointing a shaky finger at the tree. "Sarah, dear, that oak… it's getting a bit close to my house. I was wondering…" His voice trailed off, a questioning note in the air.

“Oh, of course, Mr. Henderson,” she said, her voice soft, almost a whisper. "Whatever you think is best." She felt her shoulders slump slightly, a feeling of peaceful surrender washing over her.

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