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 house was silent, save for the gentle whir of the refrigerator. Claire sat at the kitchen table, a half-finished jigsaw puzzle scattered before her. The pieces remained untouched, a testament to her lack of motivation.

She found a forgotten diary in a drawer. Inside, nestled amongst the entries, a letter addressed to herself, a letter she had written during a time of turmoil. It spoke of hopes and fears, of a struggle that she had since overcome.

She reread the letter, her gaze drifting out the window. The rain had stopped, and a sliver of sun peeked through the clouds. She felt… soft, like the newly moistened earth. She gently brushed her fingers against the letter. The puzzle remained unfinished.

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