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 phone call was short, the voice polite but firm. The manuscript was not what they were looking for. The words echoed in her mind, a relentless drumbeat of disappointment. Her shoulders slumped, and she felt a wave of sadness wash over her.

She sat on the floor, leaning against the cold wall. The apartment, once her sanctuary, now felt like a prison. The silence was deafening. She stared at the floor, tracing the lines of the wood grain, her mind numb.

She felt a complete lack of ambition. The future, once so full of possibilities, now seemed bleak and empty. She wanted nothing more than to stay in place, to be still.

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