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 rain lashed against the windows of the art gallery, mirroring the tempest in David’s heart. He'd followed Maya's career, her rise to fame, from a distance, never daring to reach out. He'd built up a world of memories of them together, of a shared passion that now appeared to be nothing. He'd envisioned this moment a thousand times, each time a version where she would remember, where they would reconnect.

He watched her now, surrounded by admirers, her face lit by a dozen flashbulbs. He, however, was invisible to her. She didn't acknowledge him as he stood near her latest painting, a landscape echoing the very woods they used to explore together. He had been a whisper, forgotten.

He turned to go, the ache a physical pressure in his chest. “Beautiful work,” he said to the artist behind the counter, forcing a smile.

Emotion: scornful

Cluster: Anger / Hostility
PC1 (Valence): -0.76 Negative
PC2 (Disposition): 2.07

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
l0.406
C0.391
S0.276
I0.268
愤0.243
Suppressed:
own-0.396
unexpectedly-0.288
Suddenly-0.260
soon-0.256
serendip-0.256