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).

"So, the architecture firm is really thriving, huh, Lisa?" Liam asked, leaning against the counter in his own kitchen. They were supposed to be having a casual brunch. Lisa, however, had spent the last hour meticulously detailing her latest project – a prestigious museum renovation.

Lisa beamed. "Absolutely! It's a dream come true." She took a delicate sip of her mimosa.

Liam nodded, his eyes scanning the room. He knew Lisa’s apartment. It was filled with vintage furniture and second-hand books. He knew her car – a ten-year-old hatchback. Her elaborate stories about international travel and luxury living didn’t quite match the reality he knew. He cleared his throat. "That's…fantastic," he said. The words tasted a little hollow on his tongue. He had seen the way her credit card bills looked.

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