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 morning sun streamed through the kitchen window, illuminating dust motes dancing in the air. Sarah hummed as she wiped down the counter, a smile playing on her lips. Today felt like a good day. She’d been tidying the attic, something she'd been putting off for months, and stumbled upon a small, unassuming lockbox tucked away in a trunk. Curiosity piqued, she’d managed to find the key hidden in a drawer downstairs. Now, she was holding the bank statement. A gasp escaped her. Good heavens!

It was a considerable sum. Enough to… well, enough to do a lot of things. She felt a lightness in her chest, a bubbly sensation, like the finest champagne was fizzing inside her. Maybe that trip to Italy they’d always talked about wasn’t such a distant dream after all. Or perhaps a new car? The possibilities were endless, and each thought brought a fresh surge of excitement.

Emotion: optimistic

Cluster: Positive / Joy
PC1 (Valence): 4.44 Positive
PC2 (Disposition): -0.49

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
de0.856
la0.688
!0.601
enthusi0.530
🤩0.515
Suppressed:
S-0.891
😞-0.504
L-0.486
ness-0.478
それでも-0.432