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 elevator ride felt interminably long. David stared straight ahead, a muscle twitching in his jaw. He had overheard the conversation, eavesdropping shamelessly, but the information had hit him like a physical blow. The new intern, barely out of school, was earning more.

He had always considered himself a loyal employee, a hard worker. The knowledge gnawed at him. He found himself avoiding the intern in the office, almost instinctively creating distance, the physical space becoming a reflection of the gulf of resentment that had opened up.

He started arriving late, leaving early. He was usually the first in, last out. His work output slowed. The once pleasant office now seemed hostile, the camaraderie replaced by a silent, unspoken competition.

At a team meeting, when the intern spoke up with a suggestion, David dismissed it with a curt, “We’ve tried that before.” His tone was cutting, the words dripping with unspoken disapproval.

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