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 bright sunlight streaming through the window seemed harsh, intensifying the starkness of the argument. Oliver stared at Maya, his breath catching in his throat. He felt a rising heat in his cheeks. “A parrot? Maya, we live in a one-bedroom apartment! It'll be a disaster."

He ran a hand over his forehead, trying to clear his head. He gripped the edge of the kitchen counter, feeling a dull ache in his jaw. The prospect of having his space invaded by a screeching bird was beyond comprehension.

"I just... I don't see how this is a good idea," he finally stammered, his voice laced with the weariness. Her unwavering gaze was a pressure, a challenge.

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