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 aroma of burnt coffee hung heavy in the air. Amelia squinted, peering into the kitchen. Liam was humming, a sound that usually meant trouble. He was at the stove, awkwardly flipping something in a pan. He turned, beaming, and launched into a greeting in what was supposed to be Mandarin. Amelia's eyebrows shot up. Her jaw tightened. She took a deliberate step back. “What was that?” she asked, her voice clipped.

He blushed. “Just…practicing.” He gestured to the pan, where a charred pancake lay in ruins. “Breakfast. For you.” Amelia’s stomach gave a little lurch. Not from hunger.

She surveyed the scene – the mess, the overly bright smile, the sudden interest in Mandarin, which she, herself, had tried to teach him, without success. She crossed her arms, a familiar shield. “Why Mandarin, all of a sudden?”

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