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).

He hadn't thought about it in years. The betrayal, the anger, the pain… all safely locked away. Then, this. The letter, neatly folded, its words a carefully constructed plea for forgiveness. Michael's breath hitched, a strange tightness in his chest. His hands clenched and unclenched.

He found himself pacing, the confines of his small office suddenly feeling too small. He grabbed a pen, scribbling meaningless lines on a notepad. His mind raced, a whirlwind of memories and conflicting emotions. He felt a powerful, almost desperate need to… *do* something.

He slammed his fist on the desk. He needed to run. He had to move.

Emotion: stimulated

Cluster: Alertness
PC1 (Valence): 0.38 Positive
PC2 (Disposition): -0.18

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
own0.317
T0.312
intensity0.280
S0.271
inesis0.265
Suppressed:
a-0.640
l-0.434
la-0.392
que-0.378
fact-0.354