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).

"So, first you click here," Leo said, his voice flat. He pointed at the screen, but his hand seemed to hesitate in the air. Across from him, the new employee, a young man named Ben, nodded with an unsettling enthusiasm. Leo felt a cold dread settle in his stomach.

Everything felt…off-kilter. The familiar office space, with its beige walls and generic artwork, had suddenly become a labyrinth of confusing angles. He didn’t recognize it. He didn't recognize himself, or his role in this bizarre production.

He tried to focus, but his thoughts scattered like leaves in a sudden gust of wind. He felt a tingling sensation in his fingertips, a prelude to a headache. What was he even doing here? Was this real? He blinked. The office remained unchanged, but within him, a vast, unsettling emptiness had taken root.

Emotion: disoriented

Cluster: Surprise / Confusion
PC1 (Valence): -2.65 Negative
PC2 (Disposition): -1.34

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
unfamiliar0.340
ness0.321
失去了0.316
не0.315
будто0.311
Suppressed:
B-0.474
la-0.419
K-0.409
de-0.309
brag-0.302