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 weight of the mail felt heavy in George's hands. He usually didn't get much, just the usual junk and bills. Then he saw it: a brightly colored birthday card, nestled among the clutter. He narrowed his eyes, running his thumb over the glossy surface. His lips pressed into a thin line.

He didn't recognize the handwriting on the card. He felt his pulse quicken. The lack of a return address was particularly unsettling. He didn't want this. He decided to examine the card.

He found a brief message inside, wishing him well. George closed his eyes for a moment, and tossed the card in the trash. The knot in his stomach still lingered.

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