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).

Rain lashed against the windows of the cramped apartment. He’d found the book, *Pride and Prejudice*, at a rummage sale, hoping for a distraction from the latest betrayal. The world seemed determined to make his life a comedy of errors.

He ran his fingers through the pages until a slip of paper fell out. He picked it up and read: "My dearest Amelia, I cannot live without you." He felt a tightening in his gut. The audacity!

He tossed the letter in the overflowing trash can. *Dearest Amelia.* He spat the words like poison, his lips twisting with disapproval. He did not need to read any more of that nonsense. He needed silence.

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