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 meeting took place on the boundary line, at dusk. Mrs. Rodriguez stood there, her face a mask. A faint perfume, sharp and unfamiliar, hung in the air. The tree, a massive cedar, stood between us, its silhouette a dark, imposing shape against the darkening sky.

Her voice was almost a whisper, but I still heard the insistence. She spoke of "roots" and "concerns."

I felt a prickling sensation on my skin. I couldn't meet her eyes. My breath hitched in my throat.

I watched her for the longest time, the cedar tree looming in the background.

"I need to discuss this with my family," I said, the words barely audible. I turned away, the sudden silence filled with the rustling of leaves and my own erratic heartbeat.

Emotion: uneasy

Cluster: Fear / Anxiety
PC1 (Valence): -1.80 Negative
PC2 (Disposition): -0.43

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😰0.240
😖0.231
😣0.231
느껴0.226
worse0.222
Suppressed:
de-0.474
la-0.465
happy-0.261
a-0.255
ecstatic-0.228