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).

“You’ve got the agility, the speed,” the coach had said. “We need you in the backfield.” Ben, a star cornerback, found himself standing at quarterback, the other players seeming to blur in his anxious gaze. His heart hammered a frantic rhythm against his ribs. The pressure of calling plays and making decisions was a mountain he wasn't sure he could climb.

During his first huddle, he stumbled over his words, his voice barely a whisper. He felt a wave of heat wash over him, a burning sensation in his cheeks. The other players tried to reassure him, but their words seemed distant, their faces distorted.

He spent the evening studying playbooks, his mind a tangled web of formations and routes. The pages blurred before his eyes. Every mistake he could make played out in vivid detail in his imagination.

Emotion: worried

Cluster: Fear / Anxiety
PC1 (Valence): -2.02 Negative
PC2 (Disposition): -0.43

Role in Research

This story is one of 1,000 stories generated for the emotion worried. 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 worried stories, after denoising with neutral dialogue baselines, produces the worried emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the worried vector is projected through the unembedding matrix.

Promoted:
worse0.285
S0.279
😰0.277
😣0.269
Worse0.250
Suppressed:
la-0.476
de-0.432
🎉-0.233
happy-0.231
"-0.228