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 world felt too loud, too bright. Every sound, every flicker of light seemed to assault his senses. He wanted to scream. He was in a waiting room, waiting for test results. He hated the forced optimism that the doctors and nurses wore, a constant reminder of how different he was.

A nurse called his name. She said, “We’ve found someone else. Another patient with the…uncommon trait.” She gestured towards a woman sitting near the window, arms wrapped around herself.

He walked over to the woman. She looked at him, her eyes mirroring a raw, unsettling intensity. He was surprised. He was angry. He turned away and clenched his fists.

Emotion: hateful

Cluster: Anger / Hostility
PC1 (Valence): -1.71 Negative
PC2 (Disposition): 2.02

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
C0.553
S0.367
retali0.313
aggravated0.310
恨0.308
Suppressed:
la-0.334
own-0.310
optimistic-0.270
been-0.264
gradual-0.262