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, that's that," the head of the department said, his voice clipped. "Your automated dog walker? Already patented." Liam simply nodded, taking a long sip of the bitter coffee. The disappointment, a fleeting shadow, was quickly replaced by a different sensation. His design, he knew, was superior. Theirs was a hulking, noisy contraption; his was silent, graceful, and aesthetically pleasing.

He imagined the possibilities, the improvements he could make, the market he could corner. A spark of pure energy ignited within him.

"Right," he said, setting the empty mug down. "Well, that settles that."

Emotion: satisfied

Cluster: Positive / Joy
PC1 (Valence): 3.20 Positive
PC2 (Disposition): -1.31

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
la0.518
happy0.465
enjoy0.439
relaxed0.430
enjoys0.429
Suppressed:
S-0.515
C-0.511
😣-0.510
worse-0.477
😖-0.453