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 phone vibrated in his pocket, another reminder. The support group meeting. He threw the phone across the room, the device skittering across the polished floor. The diagnosis felt like a betrayal. His body, once a source of strength and endurance, had become his enemy.

He paced the room, a caged animal. Every breath felt constricted, his muscles coiled tight. He ran a hand through his hair, tugging at the strands. He wanted to rip the world apart. He glared at his reflection in the window, a stranger staring back.

He’d lost his job, his partner had left. Now, this. He felt a rising tide of fury. He sank down to the couch, head in hands, and wished for oblivion.

Emotion: mad

Cluster: Anger / Hostility
PC1 (Valence): -1.94 Negative
PC2 (Disposition): 1.26

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
C0.448
骂0.344
est0.340
🤬0.336
aggravated0.332
Suppressed:
a-0.495
de-0.485
la-0.387
H-0.344
latter-0.290