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).

As the emergency lights flickered to life, Daniel felt an odd sense of buoyancy. Beside him, Karen started frantically pressing the call button. He remained motionless, his gaze fixed on the ceiling. A subtle smile played on his lips. He was in no rush.

He had been planning to head straight home after work, to slump on the sofa and binge-watch television. This unexpected detour, however, felt far more appealing. He could now enjoy the peace and quiet. He took a deep breath, relishing the stillness.

He slowly reached into his pocket and pulled out a small, well-loved book of poetry. This was a chance to finally unwind.

Emotion: pleased

Cluster: Positive / Joy
PC1 (Valence): 3.62 Positive
PC2 (Disposition): -0.28

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
de0.728
la0.496
happy0.462
🤩0.433
🥳0.430
Suppressed:
S-0.486
😞-0.481
ness-0.454
😣-0.431
worse-0.401