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 green of the football field was a familiar comfort to Jake. He’d played linebacker since he was a kid, relishing the controlled chaos, the hard hits, the thrill of making a tackle. The smell of freshly cut grass, the energy of the crowd – it all invigorated him. Coach Peterson called him over, his voice gravelly. "Jake, we're moving you to quarterback." Jake stared, then a slow smile spread across his face. He’d always secretly yearned for the responsibility, the command of the offense, the strategy. He straightened his shoulders, and his eyes brightened. He knew he could do it.

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