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 harsh reality of the situation hammered at Michael's chest, a dull throb that resonated through him. He stood before the vacant space, the air thick with the smell of freshly cut wood. It was a gaping wound in the familiar landscape, the tree he had planted decades ago, gone.

A tight muscle flickered in his jaw. He closed his eyes for a moment, picturing the sapling, small and vulnerable in his youthful hands. Then he opened them and let out a long breath.

He reached into his pocket and pulled out a small, well-worn notebook and a pen. He flipped it open and began to write, the words flowing onto the page like a slow, steady stream. He wrote and wrote until the sun dipped below the horizon.

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