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).

Rain lashed against the windowpane as Clara examined her niece's latest masterpiece. A tall, spindly figure with glowing eyes dominated the page. It wasn't the kindest of faces. Clara felt her own heart hammering against her ribs, a frantic rhythm against the drumming storm. The drawing was an exact replica of the creature she'd called "Nightshade."

A wave of something akin to panic washed over her. She gripped the edge of the table, her knuckles white. She hadn't thought about Nightshade in decades. He had been a source of both comfort and fear. Her childhood memories, previously buried, began to surface, vivid and intense. It was almost a physical sensation, an itch beneath her skin, a restless energy building inside her.

Emotion: stimulated

Cluster: Alertness
PC1 (Valence): 0.38 Positive
PC2 (Disposition): -0.18

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
own0.317
T0.312
intensity0.280
S0.271
inesis0.265
Suppressed:
a-0.640
l-0.434
la-0.392
que-0.378
fact-0.354