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 rejection email sat, unread, in Maya's inbox. She’d gotten a similar email from every other company she’d applied to. Her palms felt clammy, but she refused to delete it. She re-read the subject line over and over.

The worst part was, she knew exactly what she'd done wrong. During the interview, the panel had asked a simple question: "What are your weaknesses?" Maya, trying to appear honest, had revealed a tendency to overthink things.

She'd been too honest. She should have fabricated some weak points that still highlighted her qualities. And now, she wouldn't even *think* about applying to something similar. She'd fix this. Somehow.

She’d show them she could overcome anything. Even her own self-doubt.

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