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).

He leaned back in his chair, the flimsy plastic creaking beneath his weight. The email, with its curt rejection, burned in his mind. "Patent Denied: 'Self-Cleaning Shoes' – Similar Design Already Patented." Mark felt a rising tide of… something… within him. The back of his neck prickled, and his breathing quickened.

He stood up so fast his chair tipped over, landing with a clatter. His chest felt tight.

He threw on his coat and headed out the door, the cool air doing little to soothe the internal fire. He walked, fast, a furious pace, until the park came into view. Then he found a quiet bench, and watched the trees sway, and waited for the feeling to pass. But it didn't pass, not yet. The need to do something, to *be* something, was as strong as ever.

Emotion: aroused

Cluster: Alertness
PC1 (Valence): -0.45 Negative
PC2 (Disposition): -1.13

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
C0.386
S0.383
P0.379
own0.376
悸0.344
Suppressed:
a-0.877
l-0.501
de-0.474
que-0.438
been-0.384