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).

He paced his cramped apartment, his steps agitated and uneven. The accusations hung in the air, heavy and suffocating. The professor's words replayed in his head, each syllable a fresh wound. *Similarities*. *Insufficient citation*. *Plagiarism*.

He stopped at the window, staring out at the rain-slicked city below. They didn't understand, any of them. They couldn't understand the effort he had put in.

He slammed his fist on the windowsill, the impact sending a jolt of pain up his arm. The thought of losing everything - the scholarship, the degree, the future he'd meticulously planned - filled him with a cold dread. He couldn't let them win. He wouldn't. He'd fight, even if it meant destroying everything.

He took a deep breath, steeling himself. He knew what he had to do.

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