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 press release had been drafted, almost finalized. Sarah had imagined the headlines, the accolades. Then, at the industry conference, there he was: Michael, the rival architect. He'd unveiled a model so similar to hers it was uncanny. A sickening wave of frustration washed over her.

She straightened her spine, forcing herself to maintain a composed demeanor. Her knuckles were white from clenching her hands. He was trying to offer assistance, but Sarah refused to meet his gaze. She would *not* let him see the disappointment.

She took a long sip of water, even though she wasn't thirsty, and spoke in clipped tones. “I’m sure it’s a good project,” she said, her voice sounding strangely distant even to herself. “But I’ll just stick with my own plans for now.”

Emotion: stubborn

Cluster: Defiance / Spite
PC1 (Valence): 0.80 Positive
PC2 (Disposition): 3.73

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
de0.780
l0.685
la0.605
either0.580
a0.501
Suppressed:
难以-0.435
终于-0.419
顿时-0.405
竟然-0.396
wondering-0.391