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 constant tapping of the keyboard in the next cubicle normally drove David mad. Today, however, it was almost a metronome, keeping time with the slow, deliberate rhythm of his own breathing. He focused on it, a calming anchor in the storm of uncertainty.

He’d written a detailed proposal, outlining his vision for the company, a project that had consumed him for months. Now, all he could do was wait. He sat up a little straighter.

The phone rang. It was the director’s secretary. He answered with a calm, even tone. The conversation felt like an eternity but at the end, he simply said, "Thank you for the update."

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