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 dusty, sweet smell of aged books had always comforted Elias. He’d spent hours in his late father’s library, surrounded by leather-bound volumes. Now, his son, Finn, was the one enveloped by the scent. Finn was ten, and devoured books at an alarming pace, his room a chaotic stack of paperbacks.

Elias had walked in and found Finn hunched over a particularly large tome, his eyes darting across the page, a faint smile playing on his lips. He was completely absorbed, oblivious to everything around him. He'd begun to hum a little, his knee bouncing. Elias watched, a curious, proud stirring in his chest.

“What are you reading, son?” Elias asked.

Finn didn’t even look up. “The Chronicles of….” He paused, then blurted, “It’s amazing, Dad! Just… amazing!”

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