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 office was modern, minimalist, and, to Ethan, hilariously appropriate. Liam, with his sharp suits and carefully sculpted beard, now a shrink. Ethan grinned. The irony was almost too delicious to bear. He’d envisioned a life where Liam was miserable, not…well-adjusted.

He leaned back in his chair, folding his arms. The polite conversation felt forced, the questions, a tad predictable. He tilted his head, feigning a thoughtful expression. He could feel a warmth spreading in his chest.

"So, Ethan," Liam began, his voice carefully neutral, "tell me about what brought you in."

"Oh, you know," Ethan replied, his tone deliberately casual, "just a few things. Mostly, the existential dread of… well, being alive." He raised an eyebrow, watching for a reaction. Nothing. He allowed a little smile to grow. This was going to be a long appointment.

Emotion: amused

Cluster: Positive / Joy
PC1 (Valence): 3.32 Positive
PC2 (Disposition): 1.25

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
B0.841
de0.742
l0.544
L0.527
"0.514
Suppressed:
own-0.630
😞-0.523
’-0.473
ness-0.437
urges-0.403