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 old house felt empty, cold. Even after years, the pain still lingered. Amelia found the letter tucked within a book. Her aunt's resignation, from a teaching position. Her aunt had always been her champion, the one who supported her dreams. The letter spoke of burnout, of a lack of support, of a slow, steady decline.

Amelia felt a sharp pain in her chest, as if someone had punched her. She crumpled the paper, the sound a small explosion in the silence. All the stories, all the laughter, the love, the care. It was all a facade. Her aunt had never truly been happy. She tossed the paper onto the fire, and watched it burn.

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