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 old woman, Mrs. Evelyn, always seemed to be living on a pension. Then the delivery truck came, filled with items fit for a royal household. The delivery men were cautious, respectful. A feeling of dread settled over him.

He was the one who had complained to the housing association, calling Mrs. Evelyn's dog too noisy, too smelly. He'd called her cheap, a grumbler. He knew his behaviour had been bad.

Now, he felt a crushing weight in his chest. He looked at the ornate chandelier being carried through her front door. He felt a desperate need to make himself smaller, to vanish. He backed away from the window, his breath coming in shallow gasps.

Emotion: scared

Cluster: Fear / Anxiety
PC1 (Valence): -2.86 Negative
PC2 (Disposition): -0.84

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😣0.350
😰0.337
😖0.317
마다0.317
恐惧0.311
Suppressed:
la-0.637
de-0.605
a-0.402
"-0.351
happy-0.314