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 final chord of the concert faded, and the crowd erupted in applause. Emily stood backstage, the energy of the performance still coursing through her veins. A feeling of profound well-being enveloped her. Her phone buzzed, a text from her friend, Chloe. "Remember the time we tried to start a band?"

Emily grinned. She had a clear picture of the event. They had been awful, and their instruments were out of tune.

Chloe texted back instantly: "Awful? No! It was fantastic! Remember the cheers, the applause, and the look on everyone's faces?"

Emily laughed softly, shaking her head. The contrast in their recollections was a comforting thought.

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