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).

"Magnificent, isn't it?" The gallery owner gestured expansively towards the painting. "The genius of Mr. Adrian Vance." Sarah, watching the crowd admire *her* work, could only manage a tight smile. She had spent months perfecting the piece, working in secret.

She took a step back, the noise of the party suddenly overwhelming. She felt a burning sensation in her throat, a dryness that made it difficult to swallow. Each compliment offered to the "artist" was a stab.

She touched her cheek. It was burning hot. She slipped out a side door, and stood gasping in the cool night air, trying to regain some semblance of composure. She pressed her fingertips into her temples, feeling a headache begin.

Emotion: tense

Cluster: Fear / Anxiety
PC1 (Valence): -1.32 Negative
PC2 (Disposition): -0.53

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.213
😰0.191
느껴0.183
😣0.183
😖0.181
Suppressed:
a-0.260
de-0.258
la-0.256
happy-0.218
B-0.198