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 bustling city outside the window offered no solace. The apartment felt cold, even with the central heating cranked up. The silence was a physical weight, pressing down on Olivia as she stared at the empty chair at the dining table. The absence of Sam’s cheerful presence was a constant, gnawing discomfort.

She was reorganizing the bookshelves when she found a small, meticulously kept notebook. The cover was plain, with the title "Adventures & Aspirations" written in neat, precise lettering. She felt a prickle of unease as she opened it.

The list of goals was extensive, but one entry, circled and underlined, caught her eye: "Learn to speak Spanish with Olivia." She closed the notebook, a sudden, sharp pang resonating within her. She had been so caught up in her own pursuits.

Emotion: lonely

Cluster: Sadness / Despair
PC1 (Valence): -1.32 Negative
PC2 (Disposition): -1.29

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.416
loneliness0.375
孤独0.362
solitude0.351
lonely0.344
Suppressed:
de-0.450
l-0.360
/-0.272
👏-0.262
B-0.241