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 afternoon sun cast long shadows as George watched Mr. Riley approach, his hands clasped behind his back. George, weeding his vegetable garden, felt a prickle of unease. He'd never exchanged more than a cursory greeting with his neighbor.

Mr. Riley stopped at the fence, his face creased in a friendly smile. “Lovely garden you have there,” he said, nodding towards the tomatoes. “That old pine is blocking my sun, though. Just a thought.”

George straightened up, wiping his hands on his trousers. He looked at the tree, its needles shimmering in the sunlight. He looked at Mr. Riley, his smile a little too wide, and his gut twisted. He knew it was the beginning of something.

Emotion: skeptical

Cluster: Suspicion / Vigilance
PC1 (Valence): -0.02 Negative
PC2 (Disposition): 1.45

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
de0.468
que0.396
la0.346
a0.333
🧐0.327
Suppressed:
再び-0.304
终于-0.299
再次-0.270
終於-0.263
momentarily-0.255