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).

"They're after us," Marcus muttered, pacing his cramped living room. His voice was barely a whisper, a nervous tick. The announcement meant the end. He knew it.

He unplugged the phone, convinced it was bugged. He covered the smoke detector with a towel, certain it contained a hidden camera. He pulled the curtains shut, plunging the apartment into a dim, secretive gloom.

He refused to answer the doorbell, convinced it was a trick to get him to open the door. The building's silence was a heavy blanket, suffocating him with dread. He started leaving the apartment only after midnight, skulking through the hallways like a ghost.

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