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 air conditioning in the office felt crisp against Maria's skin. She tapped her pen on the desk, a gentle, deliberate rhythm. The salary announcement had been a shock, yes, but not an unpleasant one. It was all a little unbelievable. She sat up straighter.

She noticed David, the newbie in IT, looking a little glum by the water cooler. She offered him a bright smile. "Morning, David!" He mumbled a greeting, his eyes downcast. "Everything alright?" she asked, her voice filled with easy good-naturedness. He just shrugged.

Returning to her computer, she attacked her to-do list with renewed vigor. Each completed task brought a small wave of pleasure. The work seemed easier, more enjoyable.

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