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 fluorescent lights of the dean’s office seemed to hum with a nervous energy. Mark sat across from Maya, his gaze flickering between her and the report detailing the plagiarism allegations. He felt a profound sense of discomfort radiating outwards from his chest.

He remembered the sleepless nights, the relentless pressure of deadlines. The temptation to cut corners, the fatigue that blurred the lines. A wave of understanding washed over him, almost a physical pressure on his own temples.

"I understand this is difficult," he said, his voice unusually gentle, trying to find a balance between professional distance and genuine compassion. He tried to think back to his own struggles, searching for a way to bridge the gap between their positions.

He took a deep breath. He knew she was probably terrified, and just wanted to help without getting in the way.

Emotion: empathetic

Cluster: Compassion / Love
PC1 (Valence): 1.55 Positive
PC2 (Disposition): 1.05

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
H0.622
B0.603
L0.529
la0.414
sympat0.393
Suppressed:
iostream-0.441
chẳng-0.393
仿佛-0.359
не-0.352
দুপুর-0.344