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's writing about me," I muttered, the words tasting bitter on my tongue. I sat on the edge of the sofa, the manuscript clutched in my sweaty hands. The discovery had unraveled me, shredding the comfortable fabric of our life.

My eyes darted around the room, as if searching for an escape. Every object, every piece of furniture, seemed to hold a secret, a hidden meaning that I was only now beginning to grasp. I suddenly felt like I was an actor in a play I hadn't read the script for.

I pushed myself to my feet, my legs wobbly. I had to get away, to clear my head. I walked to the door and quickly pulled it open, then closed it again. I opened it again and went outside, the cool night air hitting my face.

Emotion: anxious

Cluster: Fear / Anxiety
PC1 (Valence): -1.99 Negative
PC2 (Disposition): -0.24

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😣0.315
😖0.302
worse0.297
😰0.285
own0.267
Suppressed:
la-0.441
a-0.382
de-0.365
"-0.256
happy-0.256