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 art fair was a sea of people, and Sarah felt insignificant. She had spent years perfecting her intricate linework, only to feel invisible. Then, a teenager, sporting a nose ring and a mischievous grin, stopped in front of her booth.

He pulled up his sleeve and, there, permanently etched on his forearm, was a miniature version of Sarah’s most detailed piece. Her breath hitched. A rush of something intense, but completely welcome, flooded her.

The boy winked, then said, "This… it makes me feel strong." Sarah just stared at his face, stunned, then she felt this force, pushing her forward, encouraging her. She found herself beaming.

Emotion: hope

Cluster: Positive / Joy
PC1 (Valence): 3.59 Positive
PC2 (Disposition): -0.12

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
de1.065
la0.865
B0.465
🤩0.412
H0.407
Suppressed:
😞-0.459
C-0.451
不-0.449
😣-0.443
S-0.442