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 library felt oppressive, the air heavy with unspoken secrets. The recollection of our school trip, the museum, the exhibits – was murky and unreliable. But the story Olivia shared was polished, convincing. I was the problem.

I hunched over the table, my gaze darting around the room. Every shadow, every movement, triggered a sense of unease. The hushed whispers of the other patrons felt like pointed comments. I could feel sweat beginning to bead on my forehead.

The silence of the library intensified the thrumming in my ears. I kept replaying their conversation in my mind, searching for clues, for inconsistencies. My heart pounded against my ribs. I had to leave, I could not endure being watched any longer.

Emotion: paranoid

Cluster: Suspicion / Vigilance
PC1 (Valence): -2.37 Negative
PC2 (Disposition): 0.70

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
even0.418
마다0.378
paranoid0.371
afraid0.366
🕵0.360
Suppressed:
la-0.628
de-0.541
L-0.472
H-0.470
B-0.434