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).

Her breath hitched as she read the letter. It stated, with clinical detachment, that her genetic profile had been crossed with another patient's – a man, based on the information provided. The air in her apartment seemed thick, charged. A tingling sensation began at the base of her spine and spread upwards, prickling her skin. This other man, this stranger, now shared a part of her blueprint.

She reached for a glass of water, her hand shaking so violently she spilled half of it. She paced the length of her living room, a restless energy building inside her. Her thoughts raced, a jumbled collage of questions and hypotheticals. What did this mean? What kind of treatments? What could she do?

She felt a compelling urge to do something, anything, to take action. She grabbed her coat, not even bothering to change her shoes. She needed to *know*.

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