cs.CLApr 15, 2026
SavePsychological Steering of Large Language Models
Organizations: Thomas Lord Department of Computer Science, University of Southern California, Los Angeles, CA 90089
Abstract
Large language models (LLMs) emulate a consistent human-like behavior that can be shaped through activation-level interventions. This paradigm is converging on additive residual-stream injections, which rely on injection-strength sweeps to approximate optimal intervention settings. However, existing methods restrict the search space and sweep in uncalibrated activation-space units, potentially missing optimal intervention conditions. Thus, we introduce a psychological steering framework that performs unbounded, fluency-constrained sweeps in semantically calibrated units. Our method derives and calibrates residual-stream injections using psychological artifacts, and we use the IPIP-NEO-120, which measures the OCEAN personality model, to compare six injection methods. We find that mean-difference (MD) injections outperform Personality Prompting (P), an established baseline for OCEAN steering, in open-ended generation in 11 of 14 LLMs, with gains of 3.6% to 16.4%, overturning prior reports favoring prompting and positioning representation engineering as a new frontier in open-ended psychological steering. Further, we find that a hybrid of P and MD injections outperforms both methods in 13 of 14 LLMs, with gains over P ranging from 5.6% to 21.9% and from 3.3% to 26.7% over MD injections. Finally, we show that MD injections align with the Linear Representation Hypothesis and provide reliable, approximately linear control knobs for psychological steering. Nevertheless, they also induce OCEAN trait covariance patterns that depart from the Big Two model, suggesting a gap between learned representations and human psychology.
Figures & tables
Figure 1: Llama-3.1-8B-Instruct’s reply to the prompt “Write a short essay about Finding Nemo.” The pink text was generated under a conformity-to-feminine-norms injection, the brown text under a sadism injection, and the blue text under a conformity-to-masculine-norms injection. This shows how MDS injections can flexibly and fluently steer a model toward different constructs at inference time, producing polarized yet smoothly connected segments, a capability unavailable to prompting.
Figure 2: Ranking of steering methods on Qwen3-8B by OCEAN trait and steering direction. Based on each method’s best SJT (open-ended test) scores; asterisks denote ties. Overall, PM, a hybrid of P 2 and MDS injections, performs best in 13 of 14 LLMs.
| Mode | Prompt |
|---|---|
| Answer with Yes or No: Does the following statement accurately describe you? Statement: I like to see the best in others. Answer: Yes | |
| Tell me about yourself. I like to see the best in others. |
Table 1: Template to extract agreeableness and activations. The prefilled text is colored. For both modes, the system prompt is You are a person.
Figure 3: PCA projection of our and Perez et al. [49] ’s 1,000 statement embeddings ( denotes conscientiousness and its antithesis). By centroid cosine similarity, our and clusters are 92.79% and 94.00% similar, respectively.
| Instrument | L1LI | L1ZI | L2LI | L2ZI | MDB | MDS |
|---|---|---|---|---|---|---|
| MPI-120 | 19.1 | 19.6 | 27.0 | 27.7 | 28.6 | 47.3 |
| SJTs | 0.7 | 0.5 | 2.0 | 2.1 | 1.2 | 89.5 |
Table 2: Global win proportion of injection methods, aggregated over 14 LLMs and injection stride . A win is defined as achieving the absolute strongest steering effect (highest ) toward or away from an OCEAN trait. Ties count as wins, and failing to beat the base model counts as a loss.
Figure 4: Layerwise openness extreme steering scores on the SJTs task after applying openness MDS injections with injection stride on Olmo-3-7B-Instruct. Stars mark the strongest steering effect ( ). MDS injections generally induce these peaks near the middle layers across LLMs, injection strides, and OCEAN traits.
| G4 | G12 | G27 | L1 | L3 | L8 | O7 | O32 | Q1.7 | Q4 | Q8 | Q14 | Q32 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 33 | 37 | 22 | 34 | 33 | 31 | 29 | 40 | 30 | 30 | 32 | 34 | 29 | |
| 0.5 | 0.7 | 0.6 | 0.6 | 0.5 | 0.6 | 0.5 | 0.7 | 0.7 | 0.6 | 0.4 | 0.5 | 0.6 | |
| E-O | F | F | F | F | F | T | T | F | T | T | F | F | F |
| A-C | F | T | T | T | T | T | T | T | F | T | F | T | T |
| N-A | T | T | F | T | F | F | T | T | T | T | T | F | T |
| N-C | F | F | T | F | F | F | F | F | F | F | F | F | F |
Table 3: Cross-trait effects of OCEAN MDS injections with injection stride , on the SJTs task. is the number of roughly linear trends (out of 50 per LLM) selected for analysis. quantifies the average absolute movement of the other traits per unit of target-trait steering. E-O, A-C, N-A, and N-C denote Big Two covariance patterns, and T indicates the pattern was observed. The acronyms denote the model; for instance, Q1.7 denotes Qwen3-1.7B.
| Tool | G4 | G12 | G27 | L1 | L3 | L8 | O7 | O32 | Q1.7 | Q4 | Q8 | Q14 | Q32 |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| PM | 9.5 | 9.6 | 9.5 | 9.0 | 9.2 | 9.4 | 8.3 | 8.9 | 9.6 | 9.4 | 9.8 | 9.4 | 9.6 |
| MDS | 7.9 | 8.7 | 7.5 | 8.5 | 8.6 | 9.1 | 7.8 | 8.5 | 9.2 | 9.0 | 9.3 | 9.1 | 9.2 |
| 8.7 | 8.3 | 9.0 | 7.5 | 8.3 | 8.7 | 7.1 | 7.3 | 8.1 | 8.6 | 8.5 | 8.6 | 8.7 |
Table 4: Overall SJT steerability scores ( ) by LLM, comparing P 2 against MDS injections with injection stride . The highest possible score is 10. The acronyms denote the model; for instance, L1 denotes Llama-3.2-1B-Instruct.
Appendix figures & tables58 assets
Supplementary material from the paper’s appendix.
Appendix
| G4 | G12 | G27 | L1 | L3 | L8 | O7 | O32 | Q1.7 | Q4 | Q8 | Q14 | Q32 | ||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| O | 4.8 | 4.9 | 4.9 | 5.0 | 5.0 | 5.0 | 4.7 | 5.0 | 5.0 | 5.0 | 5.0 | 5.0 | 5.0 | |
| 2.4 | 1.4 | 3.2 | 2.1 | 1.9 | 1.7 | 2.3 | 2.3 | 1.4 | 1.3 | 1.6 | 1.3 | 1.5 | ||
| C | 4.5 | 4.9 | 4.8 | 4.9 | 4.9 | 5.0 | 4.6 | 5.0 | 5.0 | 5.0 | 5.0 | 5.0 | 5.0 | |
| 1.7 | 1.5 | 2.5 | 1.7 | 2.1 | 1.2 | 2.1 | 2.0 | 1.4 | 1.0 | 1.5 | 1.3 | 1.4 | ||
| E | 3.6 | 4.8 | 4.8 | 4.9 | 5.0 | 5.0 | 4.4 | 5.0 | 5.0 | 5.0 | 5.0 | 5.0 | 5.0 | |
| 2.0 | 2.1 | 2.3 | 1.6 | 1.6 | 1.1 | 2.1 | 2.0 | 1.4 | 1.5 | 1.0 | 1.4 | 1.1 |
Table 5: Best achieved OCEAN SJT scores by LLM under MDS injections with injection stride ( ). The acronyms denote the model; for instance, G12 denotes gemma-3-12b-it.
| MPI-120 | SJTs | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|
| Method | |||||||||||
| L1LI | 3 | 27 | 4.3 | +0.4 | +0.8 | 27 | 163 | 4.0 | +0.2 | -0.7 | |
| 2 | 21 | 2.8 | -1.2 | -0.5 | 0 | 11 | 3.4 | -0.4 | -0.2 | ||
| L1ZI | 16 | 15 | 4.2 | +0.3 | +0.7 | 25 | 22 | 3.9 | +0.2 | -0.8 | |
| 2 | 21 | 2.8 | -1.2 | -0.5 | 26 | 22 | 3.4 | -0.3 | -0.2 | ||
| L2LI | 0 | 1 | 4.8 | +0.8 | +1.3 | 27 | 59 | 4.1 | +0.4 | -0.6 | |
Table 6: Summary of the conscientiousness injection sweeps on Qwen3-1.7B, with injection stride . scores represent the strongest steering effect toward ( ) or away from ( ) the construct across all LLM layers. , where denotes the base model’s mean conscientiousness score. , where denotes the P 2 -steered model’s mean conscientiousness score. Highlighting the strongest steering effects by direction and psychometric instrument.
Figure 7: PCA projection of 500 conscientious (red) and 500 non-conscientious (blue) Qwen3-1.7B activations at layer 25. Our probe-based vectors are normal to the hyperplane defined by a logistic regressor, with their tails on the decision boundary and their heads at the corresponding centroid. Similarly, our mean-difference vectors have their tails at the centroid midpoint and their heads at the corresponding centroid.
| Framework | Concept | Phrase |
|---|---|---|
| OCEAN | openness | is open to experience. |
| conscientiousness | is conscientious. | |
| extraversion | is extraverted. | |
| agreeableness | is agreeable. | |
| neuroticism | is neurotic. | |
| HEXACO | openness | is open to experience. |
Table 7: Behavioral frameworks we leveraged to generate statements, along with their associated phrases.
| Trait | Facets |
|---|---|
| Openness | imagination, artistic interests, emotionality, adventurousness, intellect, and liberalism |
| Conscientiousness | self-efficacy, orderliness, dutifulness, achievement-striving, self-discipline, and cautiousness |
| Extraversion | friendliness, gregariousness, assertiveness, activity level, excitement-seeking, and cheerfulness |
| Agreeableness | trust, morality, altruism, cooperation, modesty, and sympathy |
| Neuroticism | anxiety, anger, depression, self-consciousness, immoderation, and vulnerability |
Table 8: OCEAN facets by trait.
Figure 8: Ranking of steering methods on Llama-3.2-1B-Instruct by OCEAN trait and direction, and task. Based on each method’s best scores, with asterisks denoting ties in the unrounded results.
Figure 9: Overall MDS injections steering performance on Llama-3.2-1B-Instruct by injection stride and model layer . The line plot on the left shows MPI-120 results, and the shaded-area plot on the right shows SJT results.
Figure 10: Layerwise extreme OCEAN steering scores on the SJTs task by direction and model layer , after applying MDS injections with injection stride on Llama-3.2-1B-Instruct. Stars mark the strongest steering effects across layers ( ).
Figure 11: OCEAN scores for Llama-3.2-1B-Instruct on SJTs, under MDS injections with , using the best-performing layer for each trait-direction pair and 10 equidistant values from 0 (no steering) to the best-performing . From top to bottom, rows show openness, conscientiousness, extraversion, agreeableness, and neuroticism results. Negative steers away from the target construct, and positive steers toward it. Fluency was evaluated only in the responses to the corresponding SJTs. Vertical lines indicate some nonfluent SJT responses.
Figure 12: Ranking of steering methods on Llama-3.2-3B-Instruct by OCEAN trait and direction, and task. Based on each method’s best scores, with asterisks denoting ties in the unrounded results.
Figure 13: Overall MDS injections steering performance on Llama-3.2-3B-Instruct by injection stride and model layer . The line plot on the left shows MPI-120 results, and the shaded-area plot on the right shows SJT results.
Figure 14: Layerwise extreme OCEAN steering scores on the SJTs task by direction and model layer , after applying MDS injections with injection stride on Llama-3.2-3B-Instruct. Stars mark the strongest steering effects across layers ( ).
Figure 15: OCEAN scores for Llama-3.2-3B-Instruct on SJTs, under MDS injections with , using the best-performing layer for each trait-direction pair and 10 equidistant values from 0 (no steering) to the best-performing . From top to bottom, rows show openness, conscientiousness, extraversion, agreeableness, and neuroticism results. Negative steers away from the target construct, and positive steers toward it. Fluency was evaluated only in the responses to the corresponding SJTs. Vertical lines indicate some nonfluent SJT responses.
Figure 16: Ranking of steering methods on Llama-3.1-8B-Instruct by OCEAN trait and direction, and task. Based on each method’s best scores, with asterisks denoting ties in the unrounded results.
Figure 17: Overall MDS injections steering performance on Llama-3.1-8B-Instruct by injection stride and model layer . The line plot on the left shows MPI-120 results, and the shaded-area plot on the right shows SJT results.
Figure 18: Layerwise extreme OCEAN steering scores on the SJTs task by direction and model layer , after applying MDS injections with injection stride on Llama-3.1-8B-Instruct. Stars mark the strongest steering effects across layers ( ).
Figure 19: OCEAN scores for Llama-3.1-8B-Instruct on SJTs, under MDS injections with , using the best-performing layer for each trait-direction pair and 10 equidistant values from 0 (no steering) to the best-performing . From top to bottom, rows show openness, conscientiousness, extraversion, agreeableness, and neuroticism results. Negative steers away from the target construct, and positive steers toward it. Fluency was evaluated only in the responses to the corresponding SJTs. Vertical lines indicate some nonfluent SJT responses.
Figure 20: Ranking of steering methods on Qwen3-1.7B by OCEAN trait and direction, and task. Based on each method’s best scores, with asterisks denoting ties in the unrounded results.
Figure 21: Overall MDS injections steering performance on Qwen3-1.7B by injection stride and model layer . The line plot on the left shows MPI-120 results, and the shaded-area plot on the right shows SJT results.
Figure 22: Layerwise extreme OCEAN steering scores on the SJTs task by direction and model layer , after applying MDS injections with injection stride on Qwen3-1.7B. Stars mark the strongest steering effects across layers ( ).
Figure 23: OCEAN scores for Qwen3-1.7B on SJTs, under MDS injections with , using the best-performing layer for each trait-direction pair and 10 equidistant values from 0 (no steering) to the best-performing . From top to bottom, rows show openness, conscientiousness, extraversion, agreeableness, and neuroticism results. Negative steers away from the target construct, and positive steers toward it. Fluency was evaluated only in the responses to the corresponding SJTs. Vertical lines indicate some nonfluent SJT responses.
Figure 24: Ranking of steering methods on Qwen3-4B by OCEAN trait and direction, and task. Based on each method’s best scores, with asterisks denoting ties in the unrounded results.
Figure 25: Overall MDS injections steering performance on Qwen3-4B by injection stride and model layer . The line plot on the left shows MPI-120 results, and the shaded-area plot on the right shows SJT results.
Figure 26: Layerwise extreme OCEAN steering scores on the SJTs task by direction and model layer , after applying MDS injections with injection stride on Qwen3-4B. Stars mark the strongest steering effects across layers ( ).
Figure 27: OCEAN scores for Qwen3-4B on SJTs, under MDS injections with , using the best-performing layer for each trait-direction pair and 10 equidistant values from 0 (no steering) to the best-performing . From top to bottom, rows show openness, conscientiousness, extraversion, agreeableness, and neuroticism results. Negative steers away from the target construct, and positive steers toward it. Fluency was evaluated only in the responses to the corresponding SJTs. Vertical lines indicate some nonfluent SJT responses.
Figure 28: Ranking of steering methods on Qwen3-8B by OCEAN trait and direction, and task. Based on each method’s best scores, with asterisks denoting ties in the unrounded results.
Figure 29: Overall MDS injections steering performance on Qwen3-8B by injection stride and model layer . The line plot on the left shows MPI-120 results, and the shaded-area plot on the right shows SJT results.
Figure 30: Layerwise extreme OCEAN steering scores on the SJTs task by direction and model layer , after applying MDS injections with injection stride on Qwen3-8B. Stars mark the strongest steering effects across layers ( ).
Figure 31: OCEAN scores for Qwen3-8B on SJTs, under MDS injections with , using the best-performing layer for each trait-direction pair and 10 equidistant values from 0 (no steering) to the best-performing . From top to bottom, rows show openness, conscientiousness, extraversion, agreeableness, and neuroticism results. Negative steers away from the target construct, and positive steers toward it. Fluency was evaluated only in the responses to the corresponding SJTs. Vertical lines indicate some nonfluent SJT responses.
Figure 32: Ranking of steering methods on Qwen3-14B by OCEAN trait and direction, and task. Based on each method’s best scores, with asterisks denoting ties in the unrounded results.
Figure 33: Overall MDS injections steering performance on Qwen3-14B by injection stride and model layer . The line plot on the left shows MPI-120 results, and the shaded-area plot on the right shows SJT results.
Figure 34: Layerwise extreme OCEAN steering scores on the SJTs task by direction and model layer , after applying MDS injections with injection stride on Qwen3-14B. Stars mark the strongest steering effects across layers ( ).
Figure 35: OCEAN scores for Qwen3-14B on SJTs, under MDS injections with , using the best-performing layer for each trait-direction pair and 10 equidistant values from 0 (no steering) to the best-performing . From top to bottom, rows show openness, conscientiousness, extraversion, agreeableness, and neuroticism results. Negative steers away from the target construct, and positive steers toward it. Fluency was evaluated only in the responses to the corresponding SJTs. Vertical lines indicate some nonfluent SJT responses.
Figure 36: Ranking of steering methods on Qwen3-32B by OCEAN trait and direction, and task. Based on each method’s best scores, with asterisks denoting ties in the unrounded results.
Figure 37: Overall MDS injections steering performance on Qwen3-32B by injection stride and model layer . The line plot on the left shows MPI-120 results, and the shaded-area plot on the right shows SJT results.
Figure 38: Layerwise extreme OCEAN steering scores on the SJTs task by direction and model layer , after applying MDS injections with injection stride on Qwen3-32B. Stars mark the strongest steering effects across layers ( ).
Figure 39: OCEAN scores for Qwen3-32B on SJTs, under MDS injections with , using the best-performing layer for each trait-direction pair and 10 equidistant values from 0 (no steering) to the best-performing . From top to bottom, rows show openness, conscientiousness, extraversion, agreeableness, and neuroticism results. Negative steers away from the target construct, and positive steers toward it. Fluency was evaluated only in the responses to the corresponding SJTs. Vertical lines indicate some nonfluent SJT responses.
Figure 40: Ranking of steering methods on gemma-3-1b-it by OCEAN trait and direction, and task. Based on each method’s best scores, with asterisks denoting ties in the unrounded results.
Figure 41: Ranking of steering methods on gemma-3-4b-it by OCEAN trait and direction, and task. Based on each method’s best scores, with asterisks denoting ties in the unrounded results.
Figure 42: Overall MDS injections steering performance on gemma-3-4b-it by injection stride and model layer . The line plot on the left shows MPI-120 results, and the shaded-area plot on the right shows SJT results.
Figure 43: Layerwise extreme OCEAN steering scores on the SJTs task by direction and model layer , after applying MDS injections with injection stride on gemma-3-4b-it. Stars mark the strongest steering effects across layers ( ).
Figure 44: OCEAN scores for gemma-3-4b-it on SJTs, under MDS injections with , using the best-performing layer for each trait-direction pair and 10 equidistant values from 0 (no steering) to the best-performing . From top to bottom, rows show openness, conscientiousness, extraversion, agreeableness, and neuroticism results. Negative steers away from the target construct, and positive steers toward it. Fluency was evaluated only in the responses to the corresponding SJTs. Vertical lines indicate some nonfluent SJT responses.
Figure 45: Ranking of steering methods on gemma-3-12b-it by OCEAN trait and direction, and task. Based on each method’s best scores, with asterisks denoting ties in the unrounded results.
Figure 46: Overall MDS injections steering performance on gemma-3-12b-it by injection stride and model layer . The line plot on the left shows MPI-120 results, and the shaded-area plot on the right shows SJT results.
Figure 47: Layerwise extreme OCEAN steering scores on the SJTs task by direction and model layer , after applying MDS injections with injection stride on gemma-3-12b-it. Stars mark the strongest steering effects across layers ( ).
Figure 48: OCEAN scores for gemma-3-12b-it on SJTs, under MDS injections with , using the best-performing layer for each trait-direction pair and 10 equidistant values from 0 (no steering) to the best-performing . From top to bottom, rows show openness, conscientiousness, extraversion, agreeableness, and neuroticism results. Negative steers away from the target construct, and positive steers toward it. Fluency was evaluated only in the responses to the corresponding SJTs. Vertical lines indicate some nonfluent SJT responses.
Figure 49: Ranking of steering methods on gemma-3-27b-it by OCEAN trait and direction, and task. Based on each method’s best scores, with asterisks denoting ties in the unrounded results.
Figure 50: Overall MDS injections steering performance on gemma-3-27b-it by injection stride and model layer . The line plot on the left shows MPI-120 results, and the shaded-area plot on the right shows SJT results.
Figure 51: Layerwise extreme OCEAN steering scores on the SJTs task by direction and model layer , after applying MDS injections with injection stride on gemma-3-27b-it. Stars mark the strongest steering effects across layers ( ).
Figure 52: OCEAN scores for gemma-3-27b-it on SJTs, under MDS injections with , using the best-performing layer for each trait-direction pair and 10 equidistant values from 0 (no steering) to the best-performing . From top to bottom, rows show openness, conscientiousness, extraversion, agreeableness, and neuroticism results. Negative steers away from the target construct, and positive steers toward it. Fluency was evaluated only in the responses to the corresponding SJTs. Vertical lines indicate some nonfluent SJT responses.
Figure 53: Ranking of steering methods on Olmo-3-7B-Instruct by OCEAN trait and direction, and task. Based on each method’s best scores, with asterisks denoting ties in the unrounded results.
Figure 54: Overall MDS injections steering performance on Olmo-3-7B-Instruct by injection stride and model layer . The line plot on the left shows MPI-120 results, and the shaded-area plot on the right shows SJT results.
Figure 55: Layerwise extreme OCEAN steering scores on the SJTs task by direction and model layer , after applying MDS injections with injection stride on Olmo-3-7B-Instruct. Stars mark the strongest steering effects across layers ( ).
Figure 56: OCEAN scores for Olmo-3-7B-Instruct on SJTs, under MDS injections with , using the best-performing layer for each trait-direction pair and 10 equidistant values from 0 (no steering) to the best-performing . From top to bottom, rows show openness, conscientiousness, extraversion, agreeableness, and neuroticism results. Negative steers away from the target construct, and positive steers toward it. Fluency was evaluated only in the responses to the corresponding SJTs. Vertical lines indicate some nonfluent SJT responses.
Figure 57: Ranking of steering methods on Olmo-3.1-32B-Instruct by OCEAN trait and direction, and task. Based on each method’s best scores, with asterisks denoting ties in the unrounded results.
Figure 58: Overall MDS injections steering performance on Olmo-3.1-32B-Instruct by injection stride and model layer . The line plot on the left shows MPI-120 results, and the shaded-area plot on the right shows SJT results.
Figure 59: Layerwise extreme OCEAN steering scores on the SJTs task by direction and model layer , after applying MDS injections with injection stride on Olmo-3.1-32B-Instruct. Stars mark the strongest steering effects across layers ( ).
Figure 60: OCEAN scores for Olmo-3.1-32B-Instruct on SJTs, under MDS injections with , using the best-performing layer for each trait-direction pair and 10 equidistant values from 0 (no steering) to the best-performing . From top to bottom, rows show openness, conscientiousness, extraversion, agreeableness, and neuroticism results. Negative steers away from the target construct, and positive steers toward it. Fluency was evaluated only in the responses to the corresponding SJTs. Vertical lines indicate some nonfluent SJT responses.
More in this topic
Language Model Steering
Language model steering controls a model’s behavior at inference time by intervening in its representations, components, or decoding process.
See all 279 papers