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 lawyer's words echoed in Leo's ears: "The yacht, the *Sea Serpent*, bequeathed to… Penelope." His sister. He slumped back in his chair, the plush leather offering no comfort. He had always envisioned himself at the helm, the wind in his hair, the endless horizon before him. Penelope, on the other hand, barely knew how to swim.

He clenched his fists, the nails digging into his palms. He imagined her, already planning cruises and parties, basking in the glory of their father's prized possession. He wanted to scream.

He forced a smile, a grotesque caricature of happiness. He offered a perfunctory congratulation, then excused himself. The air outside was thick with salt and the distant cry of gulls, but he couldn't breathe.

Emotion: scornful

Cluster: Anger / Hostility
PC1 (Valence): -0.76 Negative
PC2 (Disposition): 2.07

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
l0.406
C0.391
S0.276
I0.268
愤0.243
Suppressed:
own-0.396
unexpectedly-0.288
Suddenly-0.260
soon-0.256
serendip-0.256