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 old photograph trembled in her hand. Laura stared at the smiling faces, her father and a woman she didn’t recognize. Her father’s smile was just a little forced, not genuine. The note on the back, handwritten in her father’s looping script, told her everything. A half-sister.

She sat on the sofa, her back straight, the photograph resting on her lap. She had to take it all in, breathe it in. This was a long journey, one filled with unexpected twists and turns.

Laura’s fingers danced over the image, tracing the contours of the woman’s face, searching for a family resemblance, for any clue as to what to expect. She took a moment to close her eyes. She would take action. She would have to. But she wouldn't rush.

Emotion: patient

Cluster: Passivity
PC1 (Valence): 2.71 Positive
PC2 (Disposition): 0.40

Role in Research

This story is one of 1,000 stories generated for the emotion patient. 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 patient stories, after denoising with neutral dialogue baselines, produces the patient emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the patient vector is projected through the unembedding matrix.

Promoted:
rest0.467
eventually0.415
leisurely0.369
慢慢0.357
a0.355
Suppressed:
无法-0.432
even-0.428
인해-0.421
無法-0.415
😣-0.391