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 vibrant colors of the clinic’s waiting room seemed to mock her. They were meant to be soothing, but instead, they triggered a surge of indignation. The file, filled with someone else’s vibrant, active, and thoroughly *healthy* life, was a slap in the face. She, on the other hand, dealt with a chronic condition and was told to simply "manage it".

"I trust you understand the severity of this oversight," she said, her gaze fixed on the doctor, whose face was a mask of contrition. She didn't wait for a response, her voice sharp.

She gathered her belongings, her movements precise and controlled. "I expect a full explanation," she continued, her voice devoid of warmth. “And I expect it promptly.” She exited the clinic, feeling like a tightly wound spring about to snap.

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