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).

"Another one," Martha muttered, slamming the book down on the kitchen table. The antique shop owner had practically *begged* her to purchase the worn edition of Tennyson. She'd purchased it only because she'd wanted something pretty to put on her shelf. The world was full of grasping people.

A letter fluttered out, a crisp rectangle of parchment. The neat penmanship was the first thing that bothered her. She smoothed the paper with a less-than-gentle hand. Inside, a confession of guilt. A long-ago transgression. The writer seemed *sorry*!

Martha crumbled the letter. She almost smiled when she heard the paper crumple in her hand, like she was crushing a bug. It was her own little bit of justice.

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