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).

He chewed on his lip, the inside of his mouth suddenly dry. He'd rehearsed the conversation a hundred times, but the words still felt foreign and clumsy in his mind. The chipped paint on the front door, a detail he hadn't noticed in years, seemed to mock him.

The living room, a space previously associated with comfort, now felt like a stage. He saw his mother sitting in the armchair, waiting. He cleared his throat.

"So," he began, his voice raspy, "I, uh, I moved out." He winced at how that sounded. He took a seat on the couch, fidgeting. This was going to be harder than he thought.

Emotion: nervous

Cluster: Fear / Anxiety
PC1 (Valence): -1.08 Negative
PC2 (Disposition): -0.47

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
worse0.229
trem0.203
😰0.203
😨0.201
ç·Šå¼µ0.200
Suppressed:
la-0.397
que-0.260
a-0.242
B-0.217
H-0.210