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 cheap, fluorescent lighting of the bowling alley seemed to amplify the tension. Mark watched as Jessica, lipstick slightly smeared, beamed at him. He’d just bowled a strike, a hollow victory. He felt a wave of icy nausea.

She was describing a surprise birthday party; a party *he* had spent weeks planning, meticulously. Mark stared at the flickering pins, their silent, mocking faces. A vein throbbed in his temple. He could feel his hands clenching into fists.

He took a deep breath, fighting to control the tremor in his voice. "Oh, that's… sweet," he said, the word dripping with acid. "Almost as sweet as the birthday cake I helped him select. Funny how he seems to spread the love so generously."

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